© 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. 7-RES-JB
    11. 20573
    Prev
    Next
    INDEX
    Explanations

    instances where something is physically attached or installed onto something else

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of words related to installation and manipulation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.67
    RESULTS
    -0.66
    é¾įå¥ij士
    -0.65
    orr
    -0.65
    ãĥ´ãĤ¡
    -0.65
    talk
    -0.64
    ierre
    -0.63
    oi
    -0.63
    yip
    -0.62
    èĪ
    -0.61
    POSITIVE LOGITS
     by
    0.85
     BY
    0.82
     anew
    0.75
     electronically
    0.75
     upon
    0.74
     unchecked
    0.73
     abl
    0.73
     prominently
    0.72
     tow
    0.71
     throughout
    0.71
    Activations Density 0.237%

    No Known Activations