© 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
    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. 45933
    Prev
    Next
    INDEX
    Explanations

    the word "end" and related terms or contexts

    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
    624
    +0.14
    0.6%
    447
    +0.14
    0.6%
    319
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.08
    160
    +0.14
    0.14
    693
    +0.11
    0.08
    Negative Logits
    issance
    -0.91
    æ©Ł
    -0.82
    esome
    -0.71
     suscept
    -0.71
    PDATE
    -0.70
     unusual
    -0.69
    hee
    -0.69
     irregular
    -0.69
    itsch
    -0.69
    RNA
    -0.67
    POSITIVE LOGITS
    angering
    1.50
    owment
    1.40
    ocrin
    1.26
    angered
    1.23
    angers
    1.23
    ocrine
    1.21
    orph
    1.19
    urance
    1.14
    points
    1.10
    game
    1.07
    Activations Density 7.510%

    No Known Activations