© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3298
    Prev
    Next
    INDEX
    Explanations

    quotations or direct speech in 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
    152
    +0.11
    0.5%
    711
    +0.10
    0.5%
    226
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.11
    0.03
    243
    +0.10
    0.03
    437
    +0.10
    0.03
    Negative Logits
    udos
    -0.69
    "},
    -0.65
    ignty
    -0.64
    Sensor
    -0.64
    mpeg
    -0.61
    urbed
    -0.61
    UTH
    -0.59
     "$:/
    -0.59
    owl
    -0.59
     que
    -0.58
    POSITIVE LOGITS
    .'"
    0.72
     Gilmore
    0.64
     Founders
    0.63
     Schwar
    0.63
     planner
    0.62
     IRA
    0.62
    ?'"
    0.61
     Sprite
    0.61
    berman
    0.61
    -'
    0.61
    Activations Density 0.469%

    No Known Activations