© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 27205
    Prev
    Next
    INDEX
    Explanations

    references to specific processes or entities related to scientific and medical terms, particularly in the context of cellular activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    475
    +0.11
    0.5%
    316
    +0.10
    0.5%
    23
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.03
    314
    +0.10
    -0.00
    288
    +0.10
    0.03
    Negative Logits
     Factor
    -0.67
     Rivals
    -0.64
    ãĥ£
    -0.62
     Estimates
    -0.61
     RAD
    -0.59
     mislead
    -0.58
     Acad
    -0.58
     proxies
    -0.58
    andise
    -0.58
     Cosponsors
    -0.57
    POSITIVE LOGITS
    ĵ
    1.53
    Ķ
    1.14
    İ
    1.01
    §
    0.93
    uity
    0.89
    agi
    0.82
    IJ
    0.82
    ights
    0.80
    Ń
    0.80
    sight
    0.80
    Activations Density 0.149%

    No Known Activations