© 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. 7275
    Prev
    Next
    INDEX
    Explanations

    the names of notable historical figures, specifically related to political contexts

    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
    756
    +0.10
    0.5%
    283
    +0.10
    0.4%
    279
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.04
    628
    +0.10
    0.03
    314
    +0.10
    0.00
    Negative Logits
    ULT
    -0.64
     prelim
    -0.62
    BOOK
    -0.62
     analy
    -0.61
     learners
    -0.59
    HAEL
    -0.59
    士
    -0.58
    ONSORED
    -0.58
    pter
    -0.58
     ultr
    -0.58
    POSITIVE LOGITS
    nesday
    1.17
    uction
    1.16
    itude
    1.15
    rick
    1.14
    estones
    1.14
    ges
    1.11
    rix
    1.09
    onia
    1.06
    gew
    1.05
    ricks
    1.04
    Activations Density 0.145%

    No Known Activations