© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8965
    Prev
    Next
    INDEX
    Explanations

    references to product recommendations and endorsements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.26
    1.2%
    430
    +0.17
    0.8%
    36
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.26
    -0.06
    153
    +0.17
    0.09
    104
    +0.11
    0.08
    Negative Logits
     eleph
    -0.87
    ĸļ
    -0.79
    ccording
    -0.77
     pione
    -0.66
    ailability
    -0.66
     Brill
    -0.66
     Parables
    -0.65
     tremend
    -0.64
    senal
    -0.63
    ©¶æ¥µ
    -0.63
    POSITIVE LOGITS
    0.61
    ÂŃ
    0.58
    yssey
    0.56
    isodes
    0.54
    âĶĢâĶĢâĶĢâĶĢ
    0.53
    iona
    0.53
    а
    0.53
    essel
    0.52
    0.52
    level
    0.51
    Activations Density 2.290%

    No Known Activations