© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    words related to stops or pauses in a sequence or journey

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stop" and its variations

    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
     suscept
    -0.81
    ophon
    -0.70
    ocene
    -0.67
    Versions
    -0.66
    aths
    -0.64
    rity
    -0.64
    yss
    -0.64
    Sov
    -0.63
    eer
    -0.62
    ighth
    -0.62
    POSITIVE LOGITS
    gap
    1.14
    watch
    1.03
    lights
    1.00
    overs
    0.80
    light
    0.77
    oppers
    0.77
    over
    0.76
    opping
    0.71
    motion
    0.70
    iem
    0.70
    Activations Density 0.037%

    No Known Activations