© 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. 3868
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'x' in various contexts

    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
    420
    +0.13
    0.6%
    348
    +0.09
    0.4%
    187
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.13
    0.02
    520
    +0.09
    0.02
    581
    +0.09
    0.01
    Negative Logits
    chairs
    -0.74
    reciation
    -0.73
    ento
    -0.72
    olkien
    -0.72
    aughs
    -0.71
    negie
    -0.69
    anguage
    -0.66
    alties
    -0.65
    ner
    -0.63
    omas
    -0.63
    POSITIVE LOGITS
     Gujar
    0.68
     drown
    0.64
     crem
    0.64
     ze
    0.63
    dayName
    0.63
     bleed
    0.61
     Nare
    0.61
     floating
    0.60
     silhou
    0.60
     Blumenthal
    0.59
    Activations Density 0.089%

    No Known Activations