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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32171
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to statistics

    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
    621
    +0.11
    0.5%
    332
    +0.10
    0.5%
    467
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    539
    +0.11
    0.29
    640
    +0.10
    0.28
    143
    +0.09
    0.27
    Negative Logits
    ĸļ
    -0.87
    roth
    -0.65
    Reloaded
    -0.65
    enment
    -0.62
    now
    -0.62
    rag
    -0.59
    ÄŁ
    -0.59
    rero
    -0.59
    ghai
    -0.58
    ngth
    -0.58
    POSITIVE LOGITS
     adj
    0.63
     berth
    0.56
     insurgents
    0.56
    ilk
    0.52
    Princ
    0.51
    mining
    0.51
    UA
    0.51
    bool
    0.50
     UNCLASSIFIED
    0.50
     compound
    0.50
    Activations Density 1.285%

    No Known Activations