© 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. 4261
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or characters, particularly those involved in critiques or reports related to notable events or media

    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
    255
    +0.10
    0.4%
    668
    +0.09
    0.4%
    637
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.10
    0.01
    749
    +0.09
    0.01
    708
    +0.09
    0.01
    Negative Logits
    incial
    -0.77
     Hungarian
    -0.77
     Bulgar
    -0.69
     Gork
    -0.69
    ework
    -0.65
    oting
    -0.64
     Bulgarian
    -0.64
    perty
    -0.63
    warts
    -0.63
     mot
    -0.62
    POSITIVE LOGITS
     Wonderland
    1.29
    ById
    0.85
    taboola
    0.81
    idge
    0.78
    ãĥīãĥ©ãĤ´ãĥ³
    0.77
     Tsukuyomi
    0.72
     Stanton
    0.71
    Elsa
    0.70
    EVA
    0.70
    enment
    0.69
    Activations Density 0.126%

    No Known Activations