© 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. 29195
    Prev
    Next
    INDEX
    Explanations

    critical discussions surrounding significant societal issues

    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
    756
    +0.17
    0.8%
    737
    +0.11
    0.5%
    401
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.17
    0.03
    679
    +0.11
    0.12
    252
    +0.11
    0.09
    Negative Logits
     imitate
    -0.71
     imitation
    -0.70
    hent
    -0.70
    ramids
    -0.68
     dup
    -0.66
    tec
    -0.65
    pattern
    -0.65
     tricks
    -0.64
    ngth
    -0.64
    Recipe
    -0.63
    POSITIVE LOGITS
     debated
    1.13
    issues
    0.99
     unresolved
    0.98
     confronting
    0.97
     contentious
    0.97
    topic
    0.96
     concern
    0.95
     debates
    0.95
     affecting
    0.94
    Issue
    0.93
    Activations Density 2.256%

    No Known Activations