© 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. 3787
    Prev
    Next
    INDEX
    Explanations

    references to notable historical or fictional characters

    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
    497
    +0.17
    0.8%
    636
    +0.12
    0.5%
    532
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.17
    0.20
    636
    +0.12
    0.09
    728
    +0.09
    0.10
    Negative Logits
     PAN
    -0.89
     SERVICES
    -0.75
     ROS
    -0.72
    ergy
    -0.69
     STUD
    -0.68
     alerts
    -0.67
     THANK
    -0.67
     TG
    -0.67
     Shelter
    -0.65
     alert
    -0.64
    POSITIVE LOGITS
    heid
    0.77
     impe
    0.76
     dictator
    0.69
     choke
    0.69
     adultery
    0.68
    emale
    0.68
    kef
    0.67
    SPONSORED
    0.66
     democratically
    0.66
     Âł Âł Âł Âł Âł Âł Âł Âł
    0.65
    Activations Density 23.835%

    No Known Activations