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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5373
    Prev
    Next
    INDEX
    Explanations

    names associated with judicial and political figures or entities

    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
    194
    +0.13
    0.6%
    462
    +0.10
    0.5%
    646
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.29
    711
    +0.10
    0.06
    194
    +0.09
    0.10
    Negative Logits
     Canaver
    -0.62
    depending
    -0.61
    IBLE
    -0.60
    ))))
    -0.51
    "))
    -0.49
    ONSORED
    -0.49
    Solution
    -0.49
    SPONSORED
    -0.47
     WRITE
    -0.47
    FontSize
    -0.47
    POSITIVE LOGITS
     and
    1.18
     or
    1.01
    ®,
    0.96
     etc
    0.90
    -,
    0.83
     AND
    0.81
     &
    0.78
     et
    0.77
    +,
    0.76
     versus
    0.74
    Activations Density 10.944%

    No Known Activations