© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    elements of formal documentation and academic records

    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
    230
    +0.12
    0.5%
    182
    +0.10
    0.4%
    410
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.04
    363
    +0.10
    0.08
    537
    +0.10
    0.09
    Negative Logits
    pmwiki
    -0.83
    natureconservancy
    -0.82
    soDeliveryDate
    -0.81
    "},"
    -0.80
    )</
    -0.80
    bryce
    -0.77
     masc
    -0.69
    ependence
    -0.68
    /_
    -0.68
    oda
    -0.68
    POSITIVE LOGITS
     recipient
    0.87
     recipients
    0.85
     respondent
    0.69
     inmate
    0.65
     scholar
    0.64
     Qi
    0.63
     receipt
    0.61
    iversary
    0.61
     postal
    0.61
     detainee
    0.61
    Activations Density 5.465%

    No Known Activations