© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14461
    Prev
    Next
    INDEX
    Explanations

    words related to fractures or breaks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "iss"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bably
    -0.80
    ITAL
    -0.71
    shaw
    -0.69
    thens
    -0.67
     Recall
    -0.67
    vised
    -0.65
    razil
    -0.64
    thening
    -0.63
    illac
    -0.63
    amac
    -0.62
    POSITIVE LOGITS
    ippi
    1.14
    andra
    0.98
    enger
    0.92
    orship
    0.90
    imo
    0.89
    lander
    0.88
    olution
    0.88
    ociation
    0.88
    auga
    0.87
    inger
    0.85
    Activations Density 0.045%

    No Known Activations