© 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. 3322
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or identities within a community

    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
    399
    +0.12
    0.6%
    42
    +0.10
    0.5%
    185
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.12
    0.08
    64
    +0.10
    -0.08
    148
    +0.10
    0.10
    Negative Logits
     Shrine
    -0.76
    tnc
    -0.72
    Äĩ
    -0.70
     Accord
    -0.69
    schild
    -0.69
    etsk
    -0.68
    atel
    -0.67
    bil
    -0.63
     borough
    -0.62
    quartered
    -0.62
    POSITIVE LOGITS
    reads
    0.70
    ESSION
    0.69
    IENT
    0.65
    Offline
    0.62
    tips
    0.62
     pg
    0.62
    fed
    0.62
    Reviewed
    0.61
     à¤
    0.61
     Nietzsche
    0.61
    Activations Density 3.665%

    No Known Activations