© 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. 31187
    Prev
    Next
    INDEX
    Explanations

    references to organizations and individuals involving political or institutional contexts

    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
    315
    +0.11
    0.5%
    467
    +0.11
    0.5%
    350
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.11
    0.11
    350
    +0.11
    0.09
    69
    +0.10
    0.08
    Negative Logits
    Registered
    -0.73
    wcsstore
    -0.72
    kB
    -0.71
    verages
    -0.71
    âĤ¬
    -0.70
    Interstitial
    -0.70
    ipedia
    -0.70
    {"
    -0.68
     denotes
    -0.66
    á¸
    -0.65
    POSITIVE LOGITS
     shadow
    0.89
     chairman
    0.77
     Prof
    0.76
     Dame
    0.76
    aints
    0.74
    ister
    0.72
     Lord
    0.72
     aide
    0.71
     Liberal
    0.71
     coroner
    0.70
    Activations Density 1.233%

    No Known Activations