© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    punctuations and quotation marks

    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
    305
    +0.12
    0.5%
    373
    +0.11
    0.5%
    120
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.12
    0.11
    101
    +0.11
    0.03
    99
    +0.10
    0.03
    Negative Logits
    establishment
    -0.70
    corruption
    -0.63
     Atmosp
    -0.61
    collar
    -0.61
    chest
    -0.60
     Assass
    -0.60
    tec
    -0.60
     establishing
    -0.60
    ospons
    -0.59
    gradient
    -0.59
    POSITIVE LOGITS
    rarily
    0.79
     glim
    0.76
    theless
    0.68
     Crom
    0.68
    hift
    0.63
     calmed
    0.63
    ILLE
    0.61
    igans
    0.60
    etting
    0.60
     Berks
    0.60
    Activations Density 0.518%

    No Known Activations