© 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. 3730
    Prev
    Next
    INDEX
    Explanations

    structured data or markup language components

    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
    481
    +0.20
    0.9%
    463
    +0.09
    0.4%
    458
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.20
    0.06
    314
    +0.09
    0.05
    656
    +0.09
    0.07
    Negative Logits
    âĢİ
    -0.66
    .):
    -0.61
    chnology
    -0.61
    ensis
    -0.59
    asus
    -0.59
    ojure
    -0.57
    Connector
    -0.56
     grips
    -0.56
     ove
    -0.56
    akra
    -0.55
    POSITIVE LOGITS
    described
    0.69
    Supplement
    0.68
     Letters
    0.68
    ãĤ±
    0.67
    ECK
    0.66
    theless
    0.65
     Supplementary
    0.64
    EEK
    0.64
     Proced
    0.63
     guiActive
    0.63
    Activations Density 2.404%

    No Known Activations