© 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. 8-RES_POST_32K-OAI
    11. 6617
    Prev
    Next
    INDEX
    Explanations

    references to a male subject, particularly using pronouns like "he" and "his."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    213
    +0.10
    0.5%
    85
    +0.09
    0.4%
    101
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.09
    762
    +0.09
    0.10
    87
    +0.09
    -0.01
    Negative Logits
     SQ
    -0.71
     Design
    -0.68
    Environmental
    -0.62
    021
    -0.60
     CoC
    -0.60
    bridge
    -0.59
    ovember
    -0.59
     Config
    -0.59
    1000
    -0.58
    DM
    -0.57
    POSITIVE LOGITS
     doubted
    0.79
     belonged
    0.74
     cried
    0.71
     preached
    0.70
     hadn
    0.69
     hugged
    0.69
    aughed
    0.69
     haun
    0.68
     WATCHED
    0.68
     screamed
    0.68
    Activations Density 0.568%

    No Known Activations