© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7173
    Prev
    Next
    INDEX
    Explanations

    information related to containers or containment, including different types of containers, uses for containers, and details about containers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.24
    1.0%
    216
    +0.16
    0.6%
    552
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.14
    326
    +0.16
    0.10
    210
    +0.14
    0.05
    Negative Logits
    doms
    -0.87
    duction
    -0.83
    urai
    -0.81
    vironment
    -0.79
    tale
    -0.79
    ctive
    -0.77
    earch
    -0.77
    amaru
    -0.77
    OTO
    -0.74
     Doodle
    -0.72
    POSITIVE LOGITS
     container
    1.08
     containers
    1.07
    ainers
    1.03
     Container
    0.99
    lain
    0.99
    mates
    0.99
     minimized
    0.92
    pipe
    0.89
    rait
    0.87
     closet
    0.86
    Activations Density 1.851%

    No Known Activations