© 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. 4335
    Prev
    Next
    INDEX
    Explanations

    key figures, actions, and concepts related to governance and policy issues

    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
    124
    +0.13
    0.6%
    218
    +0.10
    0.5%
    410
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.13
    0.07
    92
    +0.10
    0.06
    740
    +0.10
    0.06
    Negative Logits
    anchez
    -0.69
     Berm
    -0.66
    dimension
    -0.65
    ategories
    -0.64
     Canaver
    -0.61
     Bian
    -0.61
    ridor
    -0.60
     Saunders
    -0.59
     overrun
    -0.59
    jab
    -0.59
    POSITIVE LOGITS
    SPONSORED
    0.94
    izes
    0.72
    atin
    0.66
    ?
    0.66
     Allows
    0.64
    ?),
    0.64
    !?
    0.63
    ?'
    0.62
    nah
    0.61
    ?!"
    0.61
    Activations Density 1.254%

    No Known Activations