© 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 EvalsExportsAPI 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. 6208
    Prev
    Next
    INDEX
    Explanations

    references to modifications or mods in a gaming context

    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
    496
    +0.17
    0.8%
    295
    +0.11
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.17
    0.02
    61
    +0.11
    0.02
    439
    +0.10
    0.01
    Negative Logits
    lihood
    -0.82
     Situation
    -0.70
     Bucc
    -0.68
     Bulldogs
    -0.65
     Styles
    -0.64
     Messi
    -0.63
     Amend
    -0.61
     Jagu
    -0.60
     Fres
    -0.60
     Baptist
    -0.60
    POSITIVE LOGITS
    ulo
    1.27
    ding
    1.23
    ded
    1.21
    icum
    1.20
    ulus
    1.10
    der
    1.09
    elled
    1.05
    ulations
    1.01
    ulators
    0.98
    ifies
    0.98
    Activations Density 0.082%

    No Known Activations