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. 21056
    Prev
    Next
    INDEX
    Explanations

    words related to science fiction elements

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the term "sci-fi."

    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
     AVG
    -0.69
     occupancy
    -0.68
     Illum
    -0.67
     Hallow
    -0.65
     Deer
    -0.65
     Rost
    -0.63
     erection
    -0.63
     date
    -0.63
     Burr
    -0.63
     reservation
    -0.63
    POSITIVE LOGITS
    fi
    1.08
    sci
    0.96
    fiction
    0.95
    inspired
    0.93
    technical
    0.89
    tech
    0.89
    ê
    0.88
    etric
    0.87
    tal
    0.86
    hazard
    0.86
    Activations Density 0.031%

    No Known Activations