© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    gerunds and participles indicating actions or changes in state

    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
    428
    +0.11
    0.5%
    218
    +0.10
    0.5%
    435
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.11
    0.04
    602
    +0.10
    0.04
    678
    +0.10
    0.04
    Negative Logits
     landfall
    -0.93
     firewall
    -0.79
    psey
    -0.78
    ogo
    -0.78
    ught
    -0.76
    irtual
    -0.74
    enne
    -0.73
    reach
    -0.71
    amazon
    -0.70
    park
    -0.70
    POSITIVE LOGITS
    ¶æ
    0.73
     Fenrir
    0.72
     Nanto
    0.72
     Gentleman
    0.71
    âĶĢâĶĢ
    0.65
     Pros
    0.64
    âĸ¬
    0.63
     Osc
    0.61
     Akron
    0.60
    ãģ®é
    0.59
    Activations Density 0.710%

    No Known Activations