© 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. 7651
    Prev
    Next
    INDEX
    Explanations

    words expressing a positive sentiment or praise, particularly related to gratification or delicacy

    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
    590
    +0.11
    0.5%
    314
    +0.11
    0.5%
    498
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    526
    +0.11
    0.01
    326
    +0.10
    0.03
    Negative Logits
     Regulation
    -0.69
     Dru
    -0.67
     PowerPoint
    -0.66
     Equity
    -0.61
     Goose
    -0.61
     decimal
    -0.61
     Serpent
    -0.58
     Decision
    -0.58
     Weaver
    -0.58
     Dayton
    -0.57
    POSITIVE LOGITS
    uitous
    1.28
    ifying
    1.17
    iously
    1.15
    ified
    1.10
    ifiers
    1.10
    ifier
    1.07
    ific
    1.05
    ification
    1.02
    ifies
    1.01
    uit
    1.01
    Activations Density 0.109%

    No Known Activations