© 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. 20378
    Prev
    Next
    INDEX
    Explanations

    references to specific page numbers and citations in a document

    oai_token-act-pair · gpt-3.5-turbo

    numerical references and citations

    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
     disposable
    -0.69
     steady
    -0.63
    direction
    -0.63
     loyal
    -0.61
     scrut
    -0.60
     relentless
    -0.59
     wage
    -0.58
     tides
    -0.58
     stead
    -0.57
     tut
    -0.57
    POSITIVE LOGITS
     ff
    1.14
     âĨij
    0.98
    ff
    0.86
    69
    0.85
     seq
    0.85
    68
    0.83
    71
    0.83
    663
    0.82
    74
    0.81
    67
    0.81
    Activations Density 0.081%

    No Known Activations