© 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. 10-RES_POST_32K-OAI
    11. 27753
    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 @ 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
    476
    +0.11
    0.5%
    450
    +0.11
    0.5%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.02
    103
    +0.11
    0.02
    289
    +0.10
    0.01
    Negative Logits
     accountable
    -0.66
     tremend
    -0.66
    _-
    -0.59
     humidity
    -0.58
     Tyrann
    -0.56
    USD
    -0.56
    glomer
    -0.55
     salsa
    -0.55
     Nightmares
    -0.55
     fructose
    -0.54
    POSITIVE LOGITS
    adow
    1.23
    ooter
    1.22
    ield
    1.21
    ooters
    1.15
    irts
    1.10
    rine
    1.06
    adows
    1.05
    IFT
    1.01
    oulder
    1.00
    ooting
    0.97
    Activations Density 0.103%

    No Known Activations