© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or phrases associated with problems and challenges

    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
    71
    +0.11
    0.5%
    505
    +0.10
    0.4%
    56
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.11
    0.01
    136
    +0.10
    0.02
    301
    +0.10
    0.01
    Negative Logits
    Ô
    -0.72
     Annotations
    -0.72
     Startup
    -0.67
     Payment
    -0.66
    marked
    -0.65
    yip
    -0.64
    EVA
    -0.63
     Optional
    -0.62
     {*
    -0.62
     Electrical
    -0.62
    POSITIVE LOGITS
    ournament
    0.72
    bowl
    0.68
    sung
    0.67
    rito
    0.66
    liction
    0.66
    uel
    0.66
    uez
    0.65
    rib
    0.65
    usalem
    0.65
    akia
    0.64
    Activations Density 0.112%

    No Known Activations