© 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. 14138
    Prev
    Next
    INDEX
    Explanations

    numbered lists of items or elements in a document

    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
    76
    +0.06
    0.5%
    506
    +0.06
    0.5%
    708
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.06
    0.02
    435
    +0.06
    0.01
    326
    +0.06
    0.03
    Negative Logits
    iques
    -0.44
    ebook
    -0.44
    KT
    -0.36
    krit
    -0.35
    ique
    -0.35
    TF
    -0.34
    ogram
    -0.34
    BI
    -0.34
    ãĥ¼ãĥĨãĤ£
    -0.33
    issance
    -0.32
    POSITIVE LOGITS
    angled
    0.41
     collapsed
    0.37
    angles
    0.36
    thood
    0.36
     roofs
    0.35
     canopy
    0.34
     collapsing
    0.34
     afterlife
    0.33
     collapses
    0.33
    ersen
    0.33
    Activations Density 0.104%

    No Known Activations