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. 13167
    Prev
    Next
    INDEX
    Explanations

    technical information and specifications related to equipment or devices

    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
    +0.04
    0.7%
    249
    +0.03
    0.5%
    746
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.04
    0.37
    479
    +0.03
    0.07
    145
    +0.03
    0.10
    Negative Logits
    zag
    -0.22
    encer
    -0.21
    onto
    -0.20
    wid
    -0.20
    gnu
    -0.20
    andal
    -0.20
    warts
    -0.20
    encers
    -0.20
    erie
    -0.19
    within
    -0.19
    POSITIVE LOGITS
     Capacity
    0.24
     Resolution
    0.24
     Value
    0.22
     Ranking
    0.21
     Percent
    0.21
     Seconds
    0.21
     Units
    0.21
     Requirements
    0.20
     Enemies
    0.20
     Rating
    0.20
    Activations Density 15.191%

    No Known Activations