© 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. 9-RES-JB
    11. 19708
    Prev
    Next
    INDEX
    Explanations

    phrases related to states of matter and transformations between them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to physical transformations or conversions

    oai_token-act-pair · gpt-3.5-turbo
    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
     surveyed
    -0.67
     interviewed
    -0.67
     outnumbered
    -0.67
    cius
    -0.65
    @#&
    -0.61
     privilege
    -0.61
     typo
    -0.60
    athi
    -0.59
     advice
    -0.58
    bid
    -0.57
    POSITIVE LOGITS
     manageable
    1.08
    livion
    1.00
     usable
    0.94
    fledged
    0.88
    usable
    0.75
     equivalents
    0.68
     unstoppable
    0.68
    gil
    0.68
     mush
    0.67
     cohesive
    0.65
    Activations Density 0.390%

    No Known Activations