© 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. 2357
    Prev
    Next
    INDEX
    Explanations

    pairs of words related to spatial direction

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, specifically the word "and" in various contexts

    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
    aughs
    -0.74
    manship
    -0.71
    conom
    -0.70
     Devi
    -0.70
    Rocket
    -0.67
     Logged
    -0.67
    NI
    -0.67
    Beer
    -0.66
    udence
    -0.66
     Matters
    -0.65
    POSITIVE LOGITS
     periphery
    1.16
     bottom
    1.11
     upper
    1.00
     middle
    0.98
     aft
    0.97
     foremost
    0.96
     outs
    0.94
     midrange
    0.91
     underside
    0.90
     rear
    0.90
    Activations Density 0.199%

    No Known Activations