© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4198
    Prev
    Next
    INDEX
    Explanations

    references to elements of pop culture, specifically notable musical acts

    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
    218
    +0.15
    0.7%
    745
    +0.14
    0.6%
    63
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    745
    +0.15
    0.20
    63
    +0.14
    0.12
    87
    +0.11
    -0.20
    Negative Logits
     srf
    -0.70
    omination
    -0.66
     unspecified
    -0.63
     awa
    -0.63
     Crunch
    -0.63
    netflix
    -0.61
     shrimp
    -0.58
     droid
    -0.58
     synth
    -0.58
    ocity
    -0.58
    POSITIVE LOGITS
    soDeliveryDate
    0.78
    itar
    0.78
    olog
    0.73
    arist
    0.70
    writers
    0.69
    gets
    0.68
    chens
    0.66
    atl
    0.66
    kj
    0.66
    âĸij
    0.64
    Activations Density 13.194%

    No Known Activations