© 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. 7530
    Prev
    Next
    INDEX
    Explanations

    terms related to structured organizations or classifications in various 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
    479
    +0.10
    0.5%
    2
    +0.10
    0.5%
    458
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.14
    575
    +0.10
    0.10
    247
    +0.09
    0.08
    Negative Logits
    acious
    -0.76
    xious
    -0.73
     bud
    -0.69
    ctic
    -0.67
    general
    -0.66
    otte
    -0.66
    wolves
    -0.66
    bishop
    -0.66
    astical
    -0.65
    cellaneous
    -0.65
    POSITIVE LOGITS
    âĦ¢
    1.43
     Disorder
    1.27
     Facility
    1.20
     Syndrome
    1.18
     Manager
    1.14
     Award
    1.10
     Initiative
    1.09
     Month
    1.09
     Agreement
    1.08
     Replacement
    1.07
    Activations Density 1.129%

    No Known Activations