© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 18488
    Prev
    Next
    INDEX
    Explanations

    terms related to positions or locations, specifically emphasizing the back or front

    oai_token-act-pair · gpt-3.5-turbo

    references to positional or temporal locations

    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
    inia
    -0.77
    upon
    -0.69
    anmar
    -0.67
    abor
    -0.63
    atown
    -0.62
    alach
    -0.62
    artisan
    -0.62
    agra
    -0.61
    ritch
    -0.58
    heric
    -0.57
    POSITIVE LOGITS
     side
    1.03
     basis
    1.02
     sidelines
    1.00
     heels
    0.97
     shelf
    0.96
     grounds
    0.93
     doorstep
    0.89
    ieth
    0.87
     occasions
    0.86
     axis
    0.86
    Activations Density 0.170%

    No Known Activations