© 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. 5382
    Prev
    Next
    INDEX
    Explanations

    technical instructions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ideas and suggestions

    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
    cour
    -0.63
     Warrant
    -0.62
    ashi
    -0.60
    Exit
    -0.59
    utor
    -0.57
    raint
    -0.57
    rave
    -0.56
    alore
    -0.56
    Vision
    -0.54
     Coverage
    -0.53
    POSITIVE LOGITS
     either
    1.23
     anywhere
    1.18
    Either
    0.97
     whichever
    0.96
     anything
    0.96
    either
    0.92
     ANY
    0.92
     alternatively
    0.91
     optionally
    0.91
     any
    0.91
    Activations Density 0.373%

    No Known Activations