© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3805
    Prev
    Next
    INDEX
    Explanations

    discussions around the representation and challenges faced by women in various contexts

    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
    79
    +0.11
    0.5%
    608
    +0.11
    0.5%
    732
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    583
    +0.11
    0.05
    285
    +0.11
    0.05
    246
    +0.10
    0.04
    Negative Logits
     chaired
    -0.69
    ONSORED
    -0.67
    ebus
    -0.67
     (~
    -0.66
    ciation
    -0.66
     presided
    -0.65
    hiba
    -0.64
    opsis
    -0.64
    imus
    -0.63
     è£ıè
    -0.63
    POSITIVE LOGITS
     empowerment
    0.87
    icent
    0.85
     menstru
    0.82
    femin
    0.80
     herself
    0.77
     childbirth
    0.76
    cest
    0.73
     emancipation
    0.71
     reproductive
    0.70
     maid
    0.70
    Activations Density 2.342%

    No Known Activations