© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29792
    Prev
    Next
    INDEX
    Explanations

    references to categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    341
    +0.12
    0.5%
    506
    +0.10
    0.4%
    175
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.12
    0.04
    679
    +0.10
    0.06
    724
    +0.10
    0.06
    Negative Logits
    clus
    -0.63
    olini
    -0.62
     understatement
    -0.61
     unknow
    -0.59
    artifacts
    -0.58
     ado
    -0.56
    nai
    -0.55
    une
    -0.55
     +=
    -0.55
     hadn
    -0.55
    POSITIVE LOGITS
    :-
    0.90
     depending
    0.83
    %:
    0.77
    :#
    0.74
    :(
    0.69
    inces
    0.68
     simultaneously
    0.67
    igmatic
    0.67
    depending
    0.67
    ependent
    0.62
    Activations Density 0.677%

    No Known Activations