© 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. 9-RES-JB
    11. 23681
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases that indicate relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Definition
    -0.66
    adia
    -0.63
    âĿ
    -0.62
    REP
    -0.61
    itiz
    -0.60
    ounce
    -0.58
    xit
    -0.58
    IDENT
    -0.58
    Residents
    -0.58
    emade
    -0.58
    POSITIVE LOGITS
     whom
    1.10
     which
    1.07
    which
    0.93
     whose
    0.84
     whatever
    0.74
     Which
    0.72
    cause
    0.72
    whose
    0.72
     whichever
    0.71
     least
    0.70
    Activations Density 0.347%

    No Known Activations