© 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. 31654
    Prev
    Next
    INDEX
    Explanations

    ellipses and punctuation indicating hesitation or trailing thoughts

    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
    720
    +0.16
    0.7%
    373
    +0.15
    0.7%
    314
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.16
    0.07
    267
    +0.15
    0.04
    423
    +0.15
    0.04
    Negative Logits
     fide
    -0.72
     oxide
    -0.67
     Duty
    -0.55
     medal
    -0.54
     Mistress
    -0.54
    rha
    -0.53
     Anniversary
    -0.52
     Ares
    -0.52
     Roses
    -0.52
     Hero
    -0.51
    POSITIVE LOGITS
    except
    1.26
    until
    1.25
    especially
    1.18
    unless
    1.14
    which
    1.13
    particularly
    1.13
    yet
    1.11
    well
    1.09
    including
    1.07
    mostly
    1.07
    Activations Density 0.300%

    No Known Activations