© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 26963
    Prev
    Next
    INDEX
    Explanations

    elements related to vices, addiction, and societal issues

    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
    459
    +0.12
    0.6%
    309
    +0.11
    0.5%
    603
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.15
    459
    +0.11
    0.05
    652
    +0.10
    0.08
    Negative Logits
    SPONSORED
    -0.80
    Phase
    -0.74
    aido
    -0.73
    ItemImage
    -0.71
     Intermediate
    -0.70
    TION
    -0.68
    PsyNetMessage
    -0.68
     Objective
    -0.67
    Parameter
    -0.65
    RM
    -0.64
    POSITIVE LOGITS
     salesman
    1.28
     commercials
    1.04
     fetish
    0.93
     vending
    0.92
     cans
    0.88
     pedd
    0.87
     jokes
    0.86
     clenched
    0.85
     sandwiches
    0.84
     bombs
    0.83
    Activations Density 2.017%

    No Known Activations