© 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. 7425
    Prev
    Next
    INDEX
    Explanations

    references to official or regulatory documentation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "[" in the text

    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
     interf
    -0.71
     intensive
    -0.65
     regression
    -0.65
     entrepreneurship
    -0.64
     clash
    -0.63
     extinction
    -0.62
     intern
    -0.62
     forests
    -0.62
     lip
    -0.61
     maximum
    -0.61
    POSITIVE LOGITS
    Pg
    1.54
    âĢ¦]
    1.29
    sic
    1.26
    ...]
    1.21
    :]
    1.16
    ?]
    1.12
    actionDate
    1.08
    paragraph
    1.05
    note
    1.05
    src
    1.04
    Activations Density 0.035%

    No Known Activations