© 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. 3711
    Prev
    Next
    INDEX
    Explanations

    references to Members of Parliament and their titles or roles

    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
    636
    +0.14
    0.6%
    292
    +0.11
    0.5%
    659
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.14
    0.01
    640
    +0.11
    0.02
    574
    +0.09
    0.01
    Negative Logits
     indo
    -0.75
     magazine
    -0.71
     excellence
    -0.69
    advertisement
    -0.67
     mascot
    -0.65
     Excellence
    -0.65
     Corinth
    -0.64
     nominating
    -0.62
     Vulcan
    -0.61
     susp
    -0.60
    POSITIVE LOGITS
     <-
    0.91
     <+
    0.84
    irez
    0.83
    iHUD
    0.77
    rez
    0.76
    atto
    0.73
     <@
    0.72
    udeau
    0.70
    maxwell
    0.69
    raine
    0.69
    Activations Density 0.053%

    No Known Activations