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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4196
    Prev
    Next
    INDEX
    Explanations

    mentions of ranking or position within a list or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.11
    0.5%
    496
    +0.10
    0.5%
    161
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.11
    0.03
    754
    +0.10
    0.03
    311
    +0.10
    0.01
    Negative Logits
     tongue
    -0.78
     destro
    -0.78
    ersion
    -0.73
     prol
    -0.71
     nic
    -0.68
     neut
    -0.67
    redits
    -0.66
     din
    -0.64
     tongues
    -0.64
     weave
    -0.63
    POSITIVE LOGITS
    UGC
    0.86
    DIV
    0.86
    ACP
    0.73
    agate
    0.72
    NW
    0.72
     Ones
    0.72
    XL
    0.70
    EG
    0.69
    omsky
    0.69
     Generation
    0.67
    Activations Density 0.069%

    No Known Activations