© 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. 29438
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals or leadership roles in discussions of 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
    664
    +0.15
    0.7%
    373
    +0.11
    0.5%
    327
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.15
    0.06
    479
    +0.11
    -0.01
    738
    +0.09
    0.03
    Negative Logits
     ANGEL
    -0.85
     Violet
    -0.75
     Carlton
    -0.74
     Airl
    -0.71
    Angel
    -0.70
     Weir
    -0.69
    UX
    -0.67
     Cub
    -0.67
    ón
    -0.66
    acia
    -0.65
    POSITIVE LOGITS
     Pre
    2.34
     pre
    2.11
    Pre
    2.05
    pre
    1.98
     PRE
    1.86
    PRE
    1.80
     Pref
    1.53
     pref
    1.45
     prep
    1.38
     prec
    1.37
    Activations Density 4.068%

    No Known Activations