© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4007
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and package management

    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
    481
    +0.13
    0.6%
    39
    +0.12
    0.6%
    248
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.13
    0.09
    481
    +0.12
    0.14
    39
    +0.12
    0.08
    Negative Logits
    witz
    -0.79
     abound
    -0.74
     Cosponsors
    -0.71
    ãĥ¼ãĥĨ
    -0.63
     prevail
    -0.63
     Lau
    -0.63
     Aires
    -0.62
     deterrent
    -0.61
     Cohen
    -0.61
    ŃĶ
    -0.60
    POSITIVE LOGITS
     Username
    0.77
     subscribed
    0.74
    slave
    0.73
     mailed
    0.68
    oday
    0.68
     migrated
    0.68
     SOLD
    0.64
    oute
    0.63
     login
    0.63
     Donation
    0.63
    Activations Density 4.132%

    No Known Activations