© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32699
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'b' in various contexts

    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
    454
    +0.12
    0.5%
    511
    +0.10
    0.5%
    200
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.04
    103
    +0.10
    0.04
    725
    +0.09
    0.04
    Negative Logits
    zed
    -0.72
     totality
    -0.69
    ModLoader
    -0.68
     Esper
    -0.68
     altru
    -0.65
    NEY
    -0.61
     sacrific
    -0.61
     dial
    -0.61
     cooperation
    -0.60
     civ
    -0.60
    POSITIVE LOGITS
    ilts
    1.06
    uds
    1.00
    agging
    0.99
    edd
    0.95
    ead
    0.94
    ricks
    0.94
    ags
    0.94
    illed
    0.93
    orer
    0.91
    agged
    0.91
    Activations Density 0.228%

    No Known Activations