© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3376
    Prev
    Next
    INDEX
    Explanations

    terms related to sexism and sexual themes

    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
    110
    +0.13
    0.6%
    13
    +0.11
    0.5%
    568
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.13
    0.02
    13
    +0.11
    0.02
    568
    +0.11
    0.02
    Negative Logits
    ĸļ
    -0.84
    ãĥ¤
    -0.83
    Sel
    -0.78
    NL
    -0.76
    schild
    -0.75
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    Len
    -0.70
    âķIJâķIJ
    -0.70
    Ô
    -0.70
    SN
    -0.69
    POSITIVE LOGITS
    ioxide
    0.79
    obos
    0.76
    uously
    0.71
     hij
    0.65
    adesh
    0.62
     Parm
    0.62
    alez
    0.61
     gra
    0.60
     feminism
    0.60
     GOODMAN
    0.59
    Activations Density 0.054%

    No Known Activations