© 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 EvalsExportsAPI 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. 30455
    Prev
    Next
    INDEX
    Explanations

    elements related to data formatting and symbol usage

    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
    373
    +0.12
    0.6%
    764
    +0.10
    0.4%
    569
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.02
    227
    +0.10
    0.01
    409
    +0.09
    0.01
    Negative Logits
    Condition
    -0.76
    ahar
    -0.73
    atically
    -0.70
    omics
    -0.65
    Sov
    -0.64
    culosis
    -0.64
     Ada
    -0.62
     MSG
    -0.61
     Disciple
    -0.60
    imity
    -0.60
    POSITIVE LOGITS
    ¬¼
    0.71
    2018
    0.69
    2019
    0.68
    apache
    0.55
    onga
    0.54
     batt
    0.54
    oppy
    0.53
    cul
    0.52
    pite
    0.52
     Falling
    0.52
    Activations Density 0.073%

    No Known Activations