© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    specific types of Pokémon or gaming-related terminologies

    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
    763
    +0.12
    0.6%
    384
    +0.11
    0.5%
    535
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    518
    +0.12
    0.12
    580
    +0.11
    0.09
    177
    +0.09
    0.09
    Negative Logits
     Judd
    -0.79
     Lebanon
    -0.68
     Hoover
    -0.65
     Pryor
    -0.65
    anooga
    -0.63
     dissent
    -0.62
     AIDS
    -0.60
     Salman
    -0.60
     Huckabee
    -0.60
     Benson
    -0.60
    POSITIVE LOGITS
    kinson
    0.79
    hyde
    0.73
    sequ
    0.71
    itect
    0.70
    ocide
    0.70
     liner
    0.69
    hower
    0.68
     sim
    0.68
    loe
    0.68
    ccess
    0.68
    Activations Density 5.456%

    No Known Activations