© 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. 8341
    Prev
    Next
    INDEX
    Explanations

    words indicating options or comparisons

    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
    373
    +0.11
    0.5%
    520
    +0.10
    0.5%
    163
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    106
    +0.11
    0.03
    744
    +0.10
    0.02
    84
    +0.10
    0.02
    Negative Logits
     Syndrome
    -0.93
     syndrome
    -0.86
    ibilities
    -0.75
    erest
    -0.74
    hound
    -0.71
    jad
    -0.70
    agne
    -0.70
    arten
    -0.69
    ahime
    -0.67
    ){
    -0.66
    POSITIVE LOGITS
     orally
    0.91
     pertaining
    0.79
     individually
    0.79
     livest
    0.78
     domestically
    0.75
     externally
    0.75
     formally
    0.73
     emanating
    0.72
     originating
    0.72
     directly
    0.71
    Activations Density 0.100%

    No Known Activations