© 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. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3744
    Prev
    Next
    INDEX
    Explanations

    phrases indicating societal concerns or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    162
    +0.11
    0.5%
    423
    +0.11
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.11
    0.10
    101
    +0.11
    0.01
    373
    +0.10
    0.01
    Negative Logits
    bia
    -0.71
    tz
    -0.68
    abul
    -0.68
    atown
    -0.66
    EMENT
    -0.66
    acid
    -0.66
    ext
    -0.63
    blown
    -0.62
    ears
    -0.62
    ographical
    -0.62
    POSITIVE LOGITS
     Brennan
    0.68
    ©¶æ
    0.67
     UW
    0.66
     behav
    0.62
    ĸļ
    0.61
    theless
    0.61
     McKin
    0.61
     batted
    0.60
    quest
    0.60
     McConnell
    0.59
    Activations Density 1.240%

    No Known Activations