© 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. 3561
    Prev
    Next
    INDEX
    Explanations

    references to family and social relationships

    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
    642
    +0.11
    0.5%
    293
    +0.11
    0.5%
    425
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.11
    0.05
    151
    +0.11
    0.06
    659
    +0.11
    0.05
    Negative Logits
     deficits
    -0.76
     mismatch
    -0.74
     dissatisfaction
    -0.71
     offence
    -0.67
     trapping
    -0.66
     adaptations
    -0.65
     superiority
    -0.65
     discrepancies
    -0.63
     interference
    -0.63
     abnormalities
    -0.62
    POSITIVE LOGITS
    nai
    0.78
    adr
    0.77
     )]
    0.71
     Lanc
    0.71
    ogle
    0.71
    undy
    0.71
    ĪĴ
    0.69
    ften
    0.69
    qt
    0.69
     assembled
    0.67
    Activations Density 1.218%

    No Known Activations