© 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. 1-RES-JB
    11. 10205
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of a 'comeback'

    oai_token-act-pair · gpt-3.5-turbo

    references to comebacks, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.81
    agram
    -0.73
    avery
    -0.72
    apa
    -0.69
    aves
    -0.68
    ashed
    -0.67
    lements
    -0.67
    orst
    -0.67
    ascript
    -0.67
    omical
    -0.66
    POSITIVE LOGITS
     comeback
    1.32
    wcs
    0.84
     resurgence
    0.75
     shenan
    0.75
     defic
    0.73
    prise
    0.72
    ilee
    0.71
     unlaw
    0.71
     seeker
    0.69
    olicy
    0.68
    Activations Density 0.005%

    No Known Activations