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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 33320
    Prev
    Next
    INDEX
    Explanations

    technical details related to photography equipment and gear

    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
    728
    +0.05
    0.5%
    125
    +0.05
    0.5%
    61
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.05
    0.45
    6
    +0.05
    0.22
    64
    +0.04
    -0.29
    Negative Logits
    soDeliveryDate
    -0.36
    hak
    -0.29
    ickets
    -0.29
    erk
    -0.29
     Pigs
    -0.28
    TAG
    -0.28
    sell
    -0.27
    yll
    -0.27
    neys
    -0.27
    orst
    -0.27
    POSITIVE LOGITS
     curv
    0.30
     awa
    0.29
     torque
    0.28
     Citiz
    0.28
    1600
    0.28
    renheit
    0.27
    1080
    0.27
    ntil
    0.26
     blaster
    0.26
     optics
    0.26
    Activations Density 16.511%

    No Known Activations