© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 17207
    Prev
    Next
    INDEX
    Explanations

    the word "remaining" in phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or amounts that are yet to be accounted for or completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gui
    -0.74
    gio
    -0.73
    kaya
    -0.71
    imaru
    -0.70
    rection
    -0.69
    med
    -0.68
    hak
    -0.67
    mbol
    -0.67
    sych
    -0.67
    alion
    -0.67
    POSITIVE LOGITS
     undecided
    0.90
     intact
    0.86
     remaining
    0.86
     unanswered
    0.79
     unsolved
    0.78
     unbeaten
    0.77
     remnants
    0.76
     undefeated
    0.76
     fractions
    0.75
     installments
    0.73
    Activations Density 0.024%

    No Known Activations