© 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. 32433
    Prev
    Next
    INDEX
    Explanations

    the letter "G" 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
    684
    +0.11
    0.5%
    479
    +0.10
    0.5%
    418
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.05
    141
    +0.10
    0.03
    684
    +0.09
    0.03
    Negative Logits
    terday
    -0.69
     captcha
    -0.69
    actory
    -0.66
    otype
    -0.66
    undreds
    -0.63
    anwhile
    -0.63
    esides
    -0.61
     cyan
    -0.61
     hosp
    -0.59
    gaard
    -0.59
    POSITIVE LOGITS
    OLD
    1.12
    rowth
    1.05
    EST
    1.04
    roups
    1.01
    UID
    1.00
    ravity
    1.00
    OT
    0.98
    ELS
    0.96
    IF
    0.96
    UN
    0.96
    Activations Density 0.168%

    No Known Activations