© 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. 4338
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss social justice and empowerment initiatives

    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
    218
    +0.20
    0.9%
    481
    +0.16
    0.8%
    745
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.20
    0.30
    572
    +0.16
    0.18
    218
    +0.13
    0.19
    Negative Logits
     multiplier
    -0.70
    Definition
    -0.70
     diagram
    -0.68
     Profile
    -0.68
     qualitative
    -0.67
     diameter
    -0.66
     modifier
    -0.65
     excel
    -0.64
    ï
    -0.63
    ®
    -0.63
    POSITIVE LOGITS
    enegger
    0.84
    seeking
    0.71
     Frie
    0.70
     exting
    0.69
    ONSORED
    0.68
     eleph
    0.67
    ayson
    0.67
    ento
    0.66
    YA
    0.65
    avering
    0.64
    Activations Density 23.145%

    No Known Activations