© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4287
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence endings in the text

    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
    56
    +0.11
    0.5%
    389
    +0.11
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.19
    145
    +0.11
    0.12
    622
    +0.10
    0.11
    Negative Logits
     yourselves
    -0.72
     themselves
    -0.68
    ufact
    -0.59
    Experts
    -0.58
     recy
    -0.54
     experts
    -0.53
     Braz
    -0.53
    goers
    -0.53
     dstg
    -0.53
     shoppers
    -0.53
    POSITIVE LOGITS
     myself
    1.49
     my
    1.35
     My
    1.32
    My
    1.23
     I
    1.11
    my
    1.06
    I
    1.03
     MY
    1.02
     am
    0.87
    obbies
    0.74
    Activations Density 1.138%

    No Known Activations