© 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. 28003
    Prev
    Next
    INDEX
    Explanations

    references to coaching staff changes and their impacts

    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
    361
    +0.11
    0.5%
    86
    +0.10
    0.5%
    177
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.11
    0.10
    241
    +0.10
    0.08
    485
    +0.10
    0.07
    Negative Logits
     postage
    -0.83
     Sabha
    -0.78
     Mortal
    -0.69
     GOODMAN
    -0.69
     Marathon
    -0.67
    ioxid
    -0.67
    EVA
    -0.67
    Spect
    -0.67
    phrine
    -0.66
     protester
    -0.66
    POSITIVE LOGITS
     coaching
    1.41
     hire
    1.27
     hires
    1.26
     assistants
    1.21
     coached
    1.21
     hired
    1.17
     coach
    1.16
     hiring
    1.12
     coaches
    1.07
     managerial
    1.04
    Activations Density 2.722%

    No Known Activations