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

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 34017
    Prev
    Next
    INDEX
    Explanations

    text related to copying and pasting

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.15
    0.8%
    321
    +0.13
    0.7%
    187
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.15
    0.07
    288
    +0.13
    0.18
    620
    +0.11
    0.01
    Negative Logits
    hips
    -0.66
    hart
    -0.63
    axies
    -0.60
     Lights
    -0.60
    sbm
    -0.56
    ´
    -0.55
    bands
    -0.55
     Mobility
    -0.55
     Assistance
    -0.54
    guyen
    -0.53
    POSITIVE LOGITS
    urized
    1.24
     paste
    0.94
    ur
    0.88
    lete
    0.76
    uring
    0.72
    face
    0.70
    mers
    0.70
    ures
    0.68
    ure
    0.68
    ername
    0.65
    Activations Density 6.667%

    No Known Activations