© 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. 4527
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to reputation and identification

    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
    672
    +0.17
    0.8%
    420
    +0.15
    0.7%
    11
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    672
    +0.17
    0.06
    610
    +0.15
    0.04
    264
    +0.12
    0.04
    Negative Logits
    grade
    -0.76
     teaches
    -0.71
    vable
    -0.68
    antz
    -0.67
    heim
    -0.67
    mercial
    -0.66
     GEAR
    -0.66
    issions
    -0.66
    urion
    -0.66
     taught
    -0.65
    POSITIVE LOGITS
     clipboard
    0.79
     nationality
    0.79
     Hispanic
    0.72
     initials
    0.69
    Hispanic
    0.66
    UTF
    0.64
    Ali
    0.63
     Uzbek
    0.63
     Arabic
    0.62
    utf
    0.62
    Activations Density 0.623%

    No Known Activations