© 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. 3604
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical values within the text

    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
    685
    +0.10
    0.5%
    665
    +0.10
    0.4%
    673
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.10
    0.04
    462
    +0.10
    0.04
    586
    +0.10
    0.03
    Negative Logits
     fray
    -0.72
    shire
    -0.69
     Rai
    -0.65
    redo
    -0.62
     Lent
    -0.60
     RJ
    -0.59
     Bread
    -0.59
     multiply
    -0.58
    agall
    -0.57
    terness
    -0.56
    POSITIVE LOGITS
    ĸļ
    1.00
    thirds
    0.84
    schild
    0.69
    effic
    0.65
    ibrary
    0.64
    agara
    0.64
    LOCK
    0.63
    WARE
    0.63
    icht
    0.62
    berra
    0.60
    Activations Density 0.267%

    No Known Activations