© 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. 8-RES_POST_32K-OAI
    11. 7472
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.20
    0.9%
    339
    +0.09
    0.4%
    265
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.20
    0.07
    530
    +0.09
    0.05
    384
    +0.09
    0.04
    Negative Logits
     thereby
    -1.05
     respectively
    -0.77
     instead
    -0.77
     hence
    -0.74
    +.
    -0.74
     without
    -0.73
     therein
    -0.73
     whereas
    -0.72
     towards
    -0.71
     anyways
    -0.71
    POSITIVE LOGITS
    actionDate
    0.72
     Vide
    0.71
     Seym
    0.64
     Offline
    0.63
    htaking
    0.62
    ideshow
    0.61
    ĪĴ
    0.60
    ¿½
    0.58
    occup
    0.58
     Profile
    0.57
    Activations Density 0.676%

    No Known Activations