© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    phrases indicating trends and changes in data, especially related to financial or statistical 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
    127
    +0.10
    0.4%
    655
    +0.09
    0.4%
    596
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.10
    0.02
    127
    +0.09
    0.02
    375
    +0.09
    0.02
    Negative Logits
    gio
    -0.84
    Sov
    -0.78
     iss
    -0.69
    acea
    -0.65
    cat
    -0.65
    inosaur
    -0.63
    cats
    -0.63
    itaire
    -0.60
     Totally
    -0.60
     Yep
    -0.60
    POSITIVE LOGITS
    SPONSORED
    0.77
    pter
    0.72
     temptation
    0.68
    ricular
    0.68
    urden
    0.68
     levels
    0.67
     tiers
    0.66
    ighth
    0.66
    levels
    0.65
     downward
    0.64
    Activations Density 0.308%

    No Known Activations