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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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 Local
    5. 6-RES_SCL-AJT
    6. 34262
    Prev
    Next
    INDEX
    Explanations

    comments or statements expressing urgency or necessity

    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
    0.7%
    326
    +0.13
    0.6%
    455
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.09
    738
    +0.13
    0.04
    314
    +0.11
    -0.01
    Negative Logits
    stood
    -0.76
    76561
    -0.76
    itar
    -0.72
     eminent
    -0.67
    gee
    -0.66
     somew
    -0.66
     Fam
    -0.63
     Malk
    -0.63
     Mug
    -0.63
     Takeru
    -0.63
    POSITIVE LOGITS
     WATCH
    1.05
    LECT
    0.91
    ICLE
    0.80
    ORTS
    0.78
    ARD
    0.77
    %%%%
    0.76
    ']
    0.73
    CLOSE
    0.72
    %]
    0.71
    ICK
    0.71
    Activations Density 1.375%

    No Known Activations