Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4678
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and stories related to education and community issues

    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
    289
    +0.06
    0.5%
    228
    +0.06
    0.4%
    170
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.06
    0.04
    326
    +0.06
    0.04
    289
    +0.06
    0.02
    Negative Logits
    ibl
    -0.42
    IBLE
    -0.41
    fell
    -0.41
    perty
    -0.41
    meric
    -0.40
    cca
    -0.40
    Bu
    -0.39
    ishable
    -0.39
    JJ
    -0.39
    found
    -0.38
    POSITIVE LOGITS
    yles
    0.68
    rikes
    0.62
    yle
    0.55
    rike
    0.54
    yrics
    0.51
    ream
    0.51
    hops
    0.48
    urst
    0.47
    yne
    0.47
    «
    0.46
    Activations Density 0.248%

    No Known Activations