© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3741
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with firearms and ammunition specifications

    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
    323
    +0.12
    0.5%
    408
    +0.11
    0.5%
    698
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.12
    0.05
    711
    +0.11
    0.03
    107
    +0.10
    0.04
    Negative Logits
    orative
    -0.77
    ateful
    -0.74
    auna
    -0.73
    ira
    -0.72
    catentry
    -0.71
    xiety
    -0.69
    alde
    -0.68
    arte
    -0.68
    ovy
    -0.64
    unct
    -0.64
    POSITIVE LOGITS
    edIn
    0.69
     skelet
    0.67
     checkpoint
    0.64
     Shib
    0.64
     encaps
    0.64
     Alexandria
    0.61
     pub
    0.60
     Ging
    0.59
     checkpoints
    0.58
    phies
    0.58
    Activations Density 0.641%

    No Known Activations