© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29965
    Prev
    Next
    INDEX
    Explanations

    incidents involving crime, serious injuries, or public safety concerns

    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
    383
    +0.10
    0.4%
    663
    +0.09
    0.4%
    712
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.10
    0.17
    224
    +0.09
    0.18
    288
    +0.09
    0.21
    Negative Logits
     ideally
    -0.60
    hered
    -0.58
     prod
    -0.58
    essor
    -0.56
    ////////////////////////////////
    -0.55
     contemporaries
    -0.54
    >)
    -0.54
    agall
    -0.53
    eson
    -0.53
     vantage
    -0.53
    POSITIVE LOGITS
     after
    1.39
     following
    1.30
    due
    1.29
    after
    1.25
     due
    1.24
     amid
    1.21
     owing
    1.05
    follow
    0.99
     Following
    0.97
     citing
    0.96
    Activations Density 4.657%

    No Known Activations