© 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. 31263
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the letter "f" in various contexts

    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
    373
    +0.12
    0.6%
    314
    +0.12
    0.5%
    417
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.00
    254
    +0.12
    0.05
    103
    +0.11
    0.05
    Negative Logits
     ['
    -0.80
     âĢ¦"
    -0.69
     Navajo
    -0.68
     NRS
    -0.67
     Gamma
    -0.64
     Cortana
    -0.64
     SVG
    -0.64
     âĶľâĶĢâĶĢ
    -0.63
     XML
    -0.61
     Enterprise
    -0.61
    POSITIVE LOGITS
    ometimes
    1.33
    pread
    1.10
    ufficient
    1.01
    cribed
    0.99
    pecially
    0.97
    ife
    0.96
    omething
    0.95
    everal
    0.94
    overe
    0.93
    pots
    0.91
    Activations Density 0.544%

    No Known Activations