© 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. 32895
    Prev
    Next
    INDEX
    Explanations

    references to research and development activities

    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
    1.2%
    393
    +0.12
    0.9%
    732
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.39
    283
    +0.12
    0.05
    384
    +0.06
    0.11
    Negative Logits
    igmatic
    -0.45
    Lago
    -0.45
    wic
    -0.44
    ONSORED
    -0.40
    ":""},{"
    -0.39
    lights
    -0.39
     Revis
    -0.39
    lot
    -0.39
    ital
    -0.38
    itures
    -0.38
    POSITIVE LOGITS
    sonian
    0.45
     lect
    0.42
     crafts
    0.41
     consequently
    0.41
     certify
    0.40
     oversaw
    0.40
     interpret
    0.40
     pund
    0.39
     pse
    0.39
     therefore
    0.39
    Activations Density 17.346%

    No Known Activations