© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5765
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.24
    1.1%
    447
    +0.20
    1.0%
    314
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.24
    0.01
    659
    +0.20
    0.17
    232
    +0.19
    0.18
    Negative Logits
     Doomsday
    -0.74
     Competitive
    -0.70
     additive
    -0.69
     radar
    -0.69
     Scourge
    -0.67
     nefarious
    -0.67
     Carnage
    -0.66
     TBD
    -0.65
     Progress
    -0.64
     outright
    -0.63
    POSITIVE LOGITS
    hya
    0.97
    aji
    0.95
    Äĵ
    0.92
    uko
    0.90
    iko
    0.89
    ë
    0.88
    Äģ
    0.87
    ilda
    0.86
    ô
    0.86
    je
    0.86
    Activations Density 4.044%

    No Known Activations