© 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. 27063
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes of texture, color, and physical characteristics

    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
    46
    +0.11
    0.5%
    271
    +0.10
    0.5%
    678
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.11
    0.06
    351
    +0.10
    0.06
    678
    +0.10
    0.06
    Negative Logits
     reconc
    -0.75
     guiActiveUn
    -0.74
     patronage
    -0.68
    IONS
    -0.68
     Rule
    -0.68
     reperto
    -0.65
     thefts
    -0.64
     embassies
    -0.64
     collaborations
    -0.64
     Administrative
    -0.63
    POSITIVE LOGITS
    ened
    1.06
     enough
    1.04
     underneath
    0.98
    ening
    0.91
    ish
    0.90
    lier
    0.90
    ned
    0.89
    looking
    0.88
    ier
    0.86
    enough
    0.85
    Activations Density 0.289%

    No Known Activations