© 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. 7531
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or condition

    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
    66
    +0.12
    0.5%
    102
    +0.10
    0.5%
    120
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.12
    0.06
    151
    +0.10
    0.08
    102
    +0.10
    0.08
    Negative Logits
    eday
    -0.74
    arella
    -0.69
     Tools
    -0.68
    ĸļ
    -0.68
     Shutterstock
    -0.66
     Advice
    -0.64
    raltar
    -0.64
    oons
    -0.63
     Rica
    -0.63
    ĺħ
    -0.63
    POSITIVE LOGITS
     innocuous
    0.88
     disparate
    0.87
    existing
    0.84
     conflicting
    0.81
     contradictory
    0.81
     flawed
    0.80
     attractive
    0.80
    -
    0.80
     coherent
    0.80
     contentious
    0.79
    Activations Density 0.495%

    No Known Activations