© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18856
    Prev
    Next
    INDEX
    Explanations

    technical terms related to science and space

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific discovery and astronomical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.74
    iciary
    -0.70
    TPP
    -0.68
    idas
    -0.68
     entitlement
    -0.68
    ettings
    -0.67
    Priv
    -0.67
    iberal
    -0.67
     Virtue
    -0.67
    Interstitial
    -0.65
    POSITIVE LOGITS
     astronomers
    1.76
     scientists
    1.60
     astronomer
    1.57
    Scientists
    1.50
     Scientists
    1.43
     astronomy
    1.43
     astroph
    1.42
     physicists
    1.40
     biologists
    1.40
     telescopes
    1.37
    Activations Density 0.890%

    No Known Activations