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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5289
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rock" in various contexts

    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
    326
    +0.26
    0.8%
    420
    +0.17
    0.5%
    661
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.26
    0.10
    288
    +0.17
    0.10
    232
    +0.17
    0.06
    Negative Logits
    PsyNetMessage
    -1.14
     pregn
    -1.14
     Parenthood
    -1.04
     guiIcon
    -0.96
    ATIONAL
    -0.95
     blurred
    -0.94
     compan
    -0.93
    itars
    -0.90
     economical
    -0.89
    BLIC
    -0.89
    POSITIVE LOGITS
    strap
    1.82
    roach
    1.79
    tail
    1.68
    tails
    1.64
    stra
    1.57
    oops
    1.44
    warm
    1.44
    holm
    1.40
    masters
    1.39
    mith
    1.38
    Activations Density 1.476%

    No Known Activations