© 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. 3085
    Prev
    Next
    INDEX
    Explanations

    elements associated with statistical significance and data evaluation

    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
    683
    +0.12
    0.5%
    255
    +0.12
    0.5%
    168
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.12
    0.06
    255
    +0.12
    0.08
    552
    +0.09
    0.05
    Negative Logits
     infrastructure
    -0.78
     commons
    -0.69
     networking
    -0.69
     hobby
    -0.69
     locally
    -0.68
     boutique
    -0.65
     gardening
    -0.64
    vertisements
    -0.64
     collabor
    -0.63
     architecture
    -0.63
    POSITIVE LOGITS
    oglu
    0.86
    enza
    0.81
    awaru
    0.80
    iscopal
    0.76
    cens
    0.76
    aez
    0.74
    iscal
    0.74
    erry
    0.74
    lement
    0.74
    adjusted
    0.72
    Activations Density 2.015%

    No Known Activations