© 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. 6-RES-JB
    11. 14523
    Prev
    Next
    INDEX
    Explanations

    verbs related to using or performing actions with objects or tools

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to processes or functions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.76
    ãĤ´ãĥ³
    -0.72
     ?)
    -0.69
    isSpecialOrderable
    -0.69
    option
    -0.67
    actionDate
    -0.67
    uden
    -0.66
    sbm
    -0.63
    uyomi
    -0.63
    ogun
    -0.62
    POSITIVE LOGITS
     purposes
    0.79
     efficiently
    0.75
     certain
    0.72
    uate
    0.71
     various
    0.66
    enance
    0.65
     arbitrary
    0.62
    atively
    0.61
     plur
    0.61
     them
    0.61
    Activations Density 0.275%

    No Known Activations