© 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. 3521
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their effects

    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
    404
    +0.10
    0.4%
    712
    +0.09
    0.4%
    106
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.10
    0.09
    246
    +0.09
    0.11
    587
    +0.09
    0.08
    Negative Logits
     interrupted
    -0.77
     resumed
    -0.73
    iage
    -0.71
     Hearing
    -0.71
     curfew
    -0.70
     whereabouts
    -0.70
     counselling
    -0.68
     returned
    -0.68
    anwhile
    -0.67
    ifax
    -0.66
    POSITIVE LOGITS
    anchester
    0.74
    FOX
    0.73
    GW
    0.72
    kell
    0.68
    WAR
    0.66
    iah
    0.66
    mega
    0.65
    RNA
    0.64
     GDDR
    0.64
    ojure
    0.62
    Activations Density 16.955%

    No Known Activations