© 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. 27026
    Prev
    Next
    INDEX
    Explanations

    conditions and limitations within statements

    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
    98
    +0.13
    0.6%
    46
    +0.10
    0.5%
    187
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.16
    570
    +0.10
    0.03
    608
    +0.09
    0.13
    Negative Logits
    ntil
    -0.77
    iasco
    -0.73
     Quote
    -0.72
    quote
    -0.71
    once
    -0.71
     Edited
    -0.63
    wikipedia
    -0.63
    achu
    -0.63
    roo
    -0.62
    enhagen
    -0.62
    POSITIVE LOGITS
     insufficient
    1.03
     sufficient
    1.03
     sufficiently
    1.01
     suitable
    1.00
     favourable
    0.95
     demand
    0.94
    enough
    0.92
     enough
    0.90
     surplus
    0.90
     convenient
    0.88
    Activations Density 2.947%

    No Known Activations