© 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. 8-RES-JB
    11. 1189
    Prev
    Next
    INDEX
    Explanations

    terms related to various scientific disciplines, such as neuroscience, physics, biology, and mineralogy

    oai_token-act-pair · gpt-3.5-turbo

    important biological or chemical processes and their significance

    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
     Franch
    -0.73
    DCS
    -0.72
     Emails
    -0.71
     Shots
    -0.67
    nesday
    -0.65
     pics
    -0.64
    HAEL
    -0.64
    arenthood
    -0.62
     shots
    -0.62
     Hunts
    -0.62
    POSITIVE LOGITS
     biologically
    0.96
     ecosystem
    0.83
     biological
    0.81
     symb
    0.79
     chemically
    0.78
     qualitative
    0.77
     intrinsic
    0.77
     susceptibility
    0.76
     evolutionary
    0.76
     biodiversity
    0.76
    Activations Density 0.870%

    No Known Activations