© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal sentiments and experiences

    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
    +0.16
    0.7%
    395
    +0.12
    0.5%
    718
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.16
    0.05
    715
    +0.12
    0.06
    157
    +0.10
    0.05
    Negative Logits
    ymes
    -0.83
    orses
    -0.75
    pires
    -0.70
    icians
    -0.64
     Thumbnails
    -0.63
    inates
    -0.63
     Sandwich
    -0.63
    Awesome
    -0.63
     Caption
    -0.62
    Magikarp
    -0.62
    POSITIVE LOGITS
     Cull
    0.68
     coh
    0.68
     CBI
    0.66
    obin
    0.66
     fren
    0.64
     cla
    0.64
     crest
    0.63
     flank
    0.63
    govtrack
    0.62
     Ops
    0.61
    Activations Density 1.165%

    No Known Activations