© 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. 4206
    Prev
    Next
    INDEX
    Explanations

    specific brands, products, or technologies related to models and kits

    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
    320
    +0.14
    0.6%
    357
    +0.11
    0.5%
    697
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    267
    +0.11
    0.03
    475
    +0.11
    0.02
    Negative Logits
    ãĥ¼ãĤ¯
    -0.85
    osate
    -0.76
     TTL
    -0.70
     Democr
    -0.70
     cort
    -0.69
     Healer
    -0.66
    ãĥ¼ãĥ
    -0.63
     Pasadena
    -0.62
    olation
    -0.62
    stood
    -0.62
    POSITIVE LOGITS
    bush
    0.78
    oway
    0.66
    issan
    0.66
    apor
    0.65
    aucuses
    0.64
    va
    0.63
    ŃĶ
    0.63
    Va
    0.61
    akis
    0.60
    stad
    0.59
    Activations Density 0.175%

    No Known Activations