© 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. 3802
    Prev
    Next
    INDEX
    Explanations

    themes related to obsession and preoccupation with various subjects or activities

    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
    407
    +0.11
    0.5%
    109
    +0.11
    0.5%
    736
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.11
    0.02
    589
    +0.11
    0.02
    669
    +0.10
    0.02
    Negative Logits
    isSpecialOrderable
    -0.81
    OF
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    DEM
    -0.69
     Representatives
    -0.69
     iT
    -0.68
    statement
    -0.68
     opin
    -0.68
    ailable
    -0.68
     welcome
    -0.67
    POSITIVE LOGITS
     obsess
    0.98
     hobby
    0.73
    chem
    0.72
     obsession
    0.71
    ogie
    0.69
     mythology
    0.68
     obsessive
    0.68
    rix
    0.67
    vell
    0.67
     obsessed
    0.66
    Activations Density 0.282%

    No Known Activations