© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7457
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "H"

    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
    +0.16
    0.8%
    756
    +0.12
    0.6%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.16
    0.06
    15
    +0.12
    0.06
    659
    +0.09
    0.05
    Negative Logits
     Gaga
    -0.63
     Kappa
    -0.61
    ||||
    -0.60
     polio
    -0.60
     supplies
    -0.59
     gorilla
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
     targ
    -0.58
     leaking
    -0.58
     malaria
    -0.58
    POSITIVE LOGITS
    olid
    1.07
    ouses
    1.03
    uge
    1.02
    uff
    1.01
    ordes
    1.01
    ospital
    1.01
    azel
    1.01
    odder
    1.00
    undred
    0.99
    itting
    0.99
    Activations Density 0.143%

    No Known Activations