© 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. 1087
    Prev
    Next
    INDEX
    Explanations

    specific years, likely related to citations or references in documents

    oai_token-act-pair · gpt-3.5-turbo

    citations or references to academic publications

    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
    ongs
    -0.78
    geries
    -0.66
    ardless
    -0.65
    venge
    -0.61
    Bay
    -0.61
    leep
    -0.60
    gery
    -0.59
    ongh
    -0.59
    pring
    -0.59
     proced
    -0.58
    POSITIVE LOGITS
    å¹
    0.92
     ).
    0.78
     pp
    0.76
     Edition
    0.73
     edition
    0.72
    published
    0.72
     Accessed
    0.72
    ).
    0.70
     ),
    0.69
     supra
    0.68
    Activations Density 0.045%

    No Known Activations