© 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 EvalsExportsinterp-engineNEWAPI 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. 11689
    Prev
    Next
    INDEX
    Explanations

    mentions of named individuals in the context of news or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or placeholder token indicating a section break or new topic

    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
     Dickinson
    -0.67
     PLA
    -0.64
     CRC
    -0.64
     substitutes
    -0.63
     Yel
    -0.62
     totality
    -0.62
     unfocusedRange
    -0.62
     CTR
    -0.62
     CoC
    -0.61
     sinks
    -0.61
    POSITIVE LOGITS
    ceans
    1.34
    lymp
    1.31
    vernight
    1.27
    culus
    1.27
    scill
    1.26
    mega
    1.17
    liv
    1.13
    rient
    1.12
    tto
    1.12
    oops
    1.09
    Activations Density 0.030%

    No Known Activations