© 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. 4220
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to gratitude and appreciation

    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
    71
    +0.15
    0.7%
    370
    +0.10
    0.5%
    428
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.15
    0.01
    219
    +0.10
    0.02
    71
    +0.09
    0.02
    Negative Logits
    culosis
    -0.62
     Stru
    -0.61
     CFR
    -0.60
    urst
    -0.59
    utor
    -0.59
     blaster
    -0.59
    REDACTED
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.57
    uably
    -0.56
    quickShipAvailable
    -0.56
    POSITIVE LOGITS
    owship
    0.82
    eton
    0.75
    cale
    0.73
    hemy
    0.69
    steen
    0.68
    emouth
    0.66
    IENT
    0.66
    yre
    0.65
    aning
    0.64
     pri
    0.64
    Activations Density 0.097%

    No Known Activations