© 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. 3742
    Prev
    Next
    INDEX
    Explanations

    references to sports and their impact on individuals or communities

    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
    412
    +0.13
    0.6%
    497
    +0.11
    0.5%
    269
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.13
    0.06
    269
    +0.11
    0.05
    589
    +0.09
    0.05
    Negative Logits
    Wisconsin
    -0.71
     cancell
    -0.70
    VO
    -0.69
    keye
    -0.69
    dust
    -0.68
    Storm
    -0.66
    estic
    -0.66
    Exit
    -0.66
    IDS
    -0.64
     deport
    -0.63
    POSITIVE LOGITS
     Catch
    0.74
     concurrently
    0.71
     Sheldon
    0.68
     shuffle
    0.67
    ecast
    0.66
     lobb
    0.64
     Mahjong
    0.64
     QR
    0.63
     alongside
    0.63
    google
    0.63
    Activations Density 1.050%

    No Known Activations