© 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. 11360
    Prev
    Next
    INDEX
    Explanations

    number-related terms indicating a sense of "remaining"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remaining" and its context in relation to quantity or availability

    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
    gemony
    -0.76
    mbol
    -0.75
    sych
    -0.73
    gui
    -0.71
    imaru
    -0.70
     Also
    -0.68
    rection
    -0.67
    gee
    -0.67
    gio
    -0.65
    alion
    -0.64
    POSITIVE LOGITS
     portions
    0.89
     chapters
    0.88
     segments
    0.88
     sections
    0.87
     remnants
    0.87
     stages
    0.86
     fractions
    0.85
     installments
    0.84
     parts
    0.80
     avenues
    0.80
    Activations Density 0.039%

    No Known Activations