© 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. 8743
    Prev
    Next
    INDEX
    Explanations

    terms associated with academic or scholarly references

    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
    +0.15
    0.7%
    42
    +0.10
    0.5%
    567
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.15
    0.01
    435
    +0.10
    0.01
    530
    +0.09
    0.01
    Negative Logits
    hib
    -0.75
    fits
    -0.72
    ional
    -0.72
    tub
    -0.71
    fitting
    -0.68
    ikarp
    -0.67
    pole
    -0.67
    toe
    -0.66
    estic
    -0.65
    romy
    -0.65
    POSITIVE LOGITS
     Crossref
    0.93
     ISI
    0.92
     Medline
    0.74
     Scholar
    0.70
    See
    0.69
    çİĭ
    0.69
    OTHER
    0.69
    æĺ¯
    0.63
    ãĤ¦ãĤ¹
    0.63
    Tumblr
    0.62
    Activations Density 0.029%

    No Known Activations