© 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. 9920
    Prev
    Next
    INDEX
    Explanations

    the word "ke" followed by a number, possibly related to a specific keyword or code pattern in the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific prefix or stem in words

    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
     guiActiveUnfocused
    -0.69
    ains
    -0.62
    abilities
    -0.61
    oslav
    -0.61
    enegger
    -0.60
    ACY
    -0.59
    ORED
    -0.58
    姫
    -0.58
    ENTS
    -0.57
     Wales
    -0.57
    POSITIVE LOGITS
    pler
    1.17
    ller
    1.16
    jriwal
    1.14
    llers
    1.12
    ez
    1.10
    lling
    1.07
    pee
    1.05
    erk
    1.05
    lp
    1.05
    pper
    1.03
    Activations Density 0.025%

    No Known Activations