© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    technical jargon and community-specific terms

    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
    497
    +0.27
    1.3%
    218
    +0.20
    0.9%
    702
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.27
    0.00
    218
    +0.20
    0.04
    702
    +0.11
    0.03
    Negative Logits
     Franch
    -0.68
    Merit
    -0.65
     fame
    -0.65
    Sov
    -0.62
     Ark
    -0.61
     larg
    -0.61
     Oath
    -0.61
     hindsight
    -0.61
     photography
    -0.61
     Architects
    -0.60
    POSITIVE LOGITS
    atever
    0.83
    icago
    0.70
     complied
    0.70
    jriwal
    0.69
    isf
    0.69
    orage
    0.68
    aughed
    0.65
    pload
    0.64
    ãĤ¤
    0.64
     absorbed
    0.64
    Activations Density 0.745%

    No Known Activations