© 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. 5836
    Prev
    Next
    INDEX
    Explanations

    references to bills and billing amounts

    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
    314
    +0.14
    0.7%
    609
    +0.12
    0.5%
    339
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    619
    +0.14
    0.03
    163
    +0.12
    0.02
    31
    +0.11
    0.03
    Negative Logits
     Merchants
    -0.63
     Scion
    -0.60
     Galile
    -0.59
    lasses
    -0.59
    vernment
    -0.59
     ja
    -0.58
     Pv
    -0.57
     Dragonbound
    -0.57
     Governors
    -0.56
    conservancy
    -0.56
    POSITIVE LOGITS
    iard
    1.56
    owing
    1.08
    ows
    0.93
    keeping
    0.92
    boards
    0.85
    papers
    0.84
    breakers
    0.82
    igan
    0.82
    ings
    0.82
    owed
    0.82
    Activations Density 0.079%

    No Known Activations