© 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. 4385
    Prev
    Next
    INDEX
    Explanations

    prominent figures and entities in conservative media

    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
    481
    +0.11
    0.5%
    675
    +0.10
    0.5%
    725
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.11
    0.07
    620
    +0.10
    0.04
    57
    +0.09
    0.03
    Negative Logits
     smugglers
    -0.76
     Collector
    -0.72
    proc
    -0.69
     decom
    -0.68
     feasibility
    -0.68
     customs
    -0.68
    aceae
    -0.67
     mountainous
    -0.66
     mechan
    -0.66
     guiName
    -0.66
    POSITIVE LOGITS
    aturday
    0.98
    Reilly
    0.89
     Hannity
    0.88
    Fox
    0.84
    Saturday
    0.82
     occas
    0.82
     CNBC
    0.80
    NBC
    0.75
    ogyn
    0.75
     Rove
    0.73
    Activations Density 1.100%

    No Known Activations