Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8706
    Prev
    Next
    INDEX
    Explanations

    references to amounts remaining or needing to be accomplished

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "remaining" along with related numerical terms or quantifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gio
    -0.76
    gui
    -0.75
    kaya
    -0.69
    sych
    -0.69
    cause
    -0.67
    mbol
    -0.67
    rection
    -0.66
    imaru
    -0.63
     Also
    -0.63
    killer
    -0.63
    POSITIVE LOGITS
     undecided
    0.90
     intact
    0.87
     remnants
    0.83
     remaining
    0.82
     segments
    0.82
     unanswered
    0.81
     portions
    0.80
     fractions
    0.80
     sections
    0.79
     remnant
    0.79
    Activations Density 0.043%

    No Known Activations