© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings or experiences

    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
    666
    +0.11
    0.5%
    360
    +0.10
    0.5%
    286
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.11
    -0.13
    322
    +0.10
    0.10
    756
    +0.10
    0.14
    Negative Logits
     shove
    -0.78
    ļé
    -0.74
    "—
    -0.65
    )."
    -0.64
    .")
    -0.63
    ").
    -0.63
     accommod
    -0.62
    ."
    -0.62
     theirs
    -0.61
     pretend
    -0.61
    POSITIVE LOGITS
    cellaneous
    0.76
    edit
    0.76
     Fenrir
    0.70
     --------------------
    0.68
    ashtra
    0.68
    igl
    0.67
    Edit
    0.67
    ench
    0.66
    PDATED
    0.65
    ========
    0.65
    Activations Density 9.982%

    No Known Activations