© 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. 8607
    Prev
    Next
    INDEX
    Explanations

    repetitive uses of the word "so."

    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
    468
    +0.12
    0.6%
    55
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.12
    0.09
    55
    +0.11
    0.09
    559
    +0.10
    0.06
    Negative Logits
     Altern
    -0.60
     Purg
    -0.57
     Advantage
    -0.57
     Alpine
    -0.54
     arcs
    -0.53
     expectancy
    -0.53
     Hearing
    -0.52
    nings
    -0.52
     Halls
    -0.52
     Peninsula
    -0.51
    POSITIVE LOGITS
    bered
    1.37
    oths
    1.27
    apy
    1.26
    othe
    1.23
    othes
    1.15
    oner
    1.12
     far
    1.09
    ooo
    1.05
    oooo
    1.04
    aps
    1.01
    Activations Density 0.330%

    No Known Activations