© 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. 26877
    Prev
    Next
    INDEX
    Explanations

    mentions of banks and their influence or activities

    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
    26
    +0.11
    0.5%
    628
    +0.10
    0.4%
    679
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.11
    0.02
    700
    +0.10
    0.03
    288
    +0.08
    0.03
    Negative Logits
    ategory
    -0.69
     Reincarn
    -0.66
     Leone
    -0.66
    enegger
    -0.66
    Pg
    -0.65
    ESSION
    -0.61
    ITH
    -0.61
    yang
    -0.60
    DERR
    -0.60
    apy
    -0.59
    POSITIVE LOGITS
    rupt
    1.13
    ers
    1.08
    ership
    0.97
    er
    0.91
    rage
    0.78
    rator
    0.77
    ector
    0.73
    erers
    0.72
    ifier
    0.72
    heim
    0.72
    Activations Density 0.251%

    No Known Activations