© 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. 28099
    Prev
    Next
    INDEX
    Explanations

    references to specific types of accounts or attributes related to cryptocurrency or digital identities

    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
    725
    +0.10
    0.5%
    363
    +0.10
    0.5%
    189
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.08
    314
    +0.10
    -0.00
    530
    +0.10
    0.05
    Negative Logits
    roman
    -0.89
    andals
    -0.82
    ades
    -0.71
    gaard
    -0.71
    adem
    -0.70
    orting
    -0.68
    atz
    -0.66
    ÅŁ
    -0.66
    hen
    -0.66
    hai
    -0.66
    POSITIVE LOGITS
    NAME
    0.85
    VOL
    0.79
    NER
    0.78
    NING
    0.77
    FILE
    0.77
    GROUP
    0.77
    LESS
    0.76
    STON
    0.76
    FOR
    0.76
    PLAY
    0.75
    Activations Density 0.795%

    No Known Activations