© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    actions related to pressing or pushing

    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
    204
    +0.15
    0.7%
    745
    +0.14
    0.7%
    538
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.15
    0.02
    204
    +0.14
    0.02
    374
    +0.14
    0.02
    Negative Logits
     Appears
    -0.69
    agascar
    -0.65
    owan
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    RIP
    -0.64
     Glob
    -0.62
     Cheney
    -0.62
     Elliott
    -0.62
    ruciating
    -0.60
    bard
    -0.60
    POSITIVE LOGITS
     inquiry
    0.77
    tone
    0.74
    izons
    0.71
     realism
    0.69
    asking
    0.69
     modernization
    0.67
     selector
    0.67
     fingert
    0.65
     suggestion
    0.65
     forefront
    0.65
    Activations Density 0.330%

    No Known Activations