© 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. 4060
    Prev
    Next
    INDEX
    Explanations

    significant entities related to law and crime context

    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
    218
    +0.14
    0.6%
    314
    +0.11
    0.5%
    451
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.14
    0.08
    437
    +0.11
    0.12
    347
    +0.10
    0.14
    Negative Logits
     Strongh
    -0.91
     Rebellion
    -0.75
    icans
    -0.73
    Marginal
    -0.71
    heit
    -0.71
    mosp
    -0.69
     Bom
    -0.69
    emen
    -0.69
    lees
    -0.69
    ggles
    -0.68
    POSITIVE LOGITS
     inspiration
    0.79
     memor
    0.72
     resemb
    0.69
     eleph
    0.67
     pione
    0.64
     prominently
    0.64
    appropriately
    0.62
    âĸĦ
    0.61
     quir
    0.61
     intel
    0.60
    Activations Density 11.077%

    No Known Activations