© 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 EvalsExportsAPI 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. 12796
    Prev
    Next
    INDEX
    Explanations

    references to car brands and models

    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
    159
    +0.20
    0.6%
    556
    +0.18
    0.5%
    328
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.20
    0.09
    404
    +0.18
    0.08
    326
    +0.15
    0.11
    Negative Logits
    lehem
    -1.06
    abase
    -1.01
    natureconservancy
    -1.00
    \<
    -0.97
    Spread
    -0.94
     tantal
    -0.92
     slender
    -0.92
    ModLoader
    -0.89
     glim
    -0.86
     conveniently
    -0.86
    POSITIVE LOGITS
    backer
    1.40
    kefeller
    1.24
     CTR
    1.06
    ordan
    1.06
    istance
    1.01
    zl
    1.01
    heed
    0.99
    restling
    0.99
    olerance
    0.96
    issance
    0.95
    Activations Density 2.816%

    No Known Activations