© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    the word "that" and its variations in various contexts

    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
    393
    +0.17
    0.8%
    655
    +0.14
    0.7%
    679
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.17
    0.15
    139
    +0.14
    0.13
    551
    +0.14
    0.13
    Negative Logits
     guessing
    -0.61
    hips
    -0.60
    ONE
    -0.58
     boarding
    -0.57
     Provision
    -0.55
    Desk
    -0.54
    river
    -0.54
    hip
    -0.53
    aciously
    -0.53
     Synd
    -0.52
    POSITIVE LOGITS
     accompanies
    1.21
     encompasses
    1.18
     resembles
    1.16
     exceeds
    1.13
     includes
    1.13
     involves
    1.12
     dominates
    1.11
     spans
    1.11
     extends
    1.10
     incorporates
    1.09
    Activations Density 1.415%

    No Known Activations