© 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 EvalsExportsAPI 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. 10367
    Prev
    Next
    INDEX
    Explanations

    commands and instructions for technical tasks or programming

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to navigating file systems and executing commands

    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
     celebrations
    -0.66
     benefited
    -0.66
     premie
    -0.65
     unve
    -0.64
    iday
    -0.63
     depended
    -0.63
     afterlife
    -0.63
    "}],"
    -0.63
     royalty
    -0.63
     audiences
    -0.62
    POSITIVE LOGITS
     preferably
    0.97
    cknow
    0.91
    STEP
    0.84
     [+
    0.83
    Remove
    0.83
    FTWARE
    0.83
     Replace
    0.83
    epad
    0.82
     Remove
    0.81
     Insert
    0.81
    Activations Density 0.669%

    No Known Activations