© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly women and their roles or actions 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
    306
    +0.14
    0.6%
    264
    +0.13
    0.6%
    340
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    476
    +0.13
    0.02
    417
    +0.12
    0.03
    Negative Logits
     relapse
    -0.74
     bouncing
    -0.67
     impuls
    -0.66
     apart
    -0.64
    ivism
    -0.64
     fentanyl
    -0.64
     Logged
    -0.63
    nuts
    -0.63
    glers
    -0.63
     reactive
    -0.62
    POSITIVE LOGITS
     Hath
    0.74
    ITE
    0.66
    ä¸ī
    0.66
     Towers
    0.66
    arth
    0.66
    enment
    0.65
    mson
    0.65
    utical
    0.65
    oise
    0.64
    ħĭ
    0.64
    Activations Density 0.229%

    No Known Activations