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. 15324
    Prev
    Next
    INDEX
    Explanations

    words related to intelligence, creativity, and resourcefulness

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of intelligence or cleverness

    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
    asta
    -0.69
    Aff
    -0.65
    emb
    -0.65
    ICAN
    -0.63
    IGH
    -0.62
    astered
    -0.62
    aru
    -0.62
     Alive
    -0.61
    forums
    -0.61
    ategory
    -0.61
    POSITIVE LOGITS
     tact
    0.93
    ly
    0.90
     tricks
    0.90
     ploy
    0.86
    NESS
    0.85
     manipulation
    0.85
     clever
    0.83
     twist
    0.83
     genius
    0.83
     satir
    0.82
    Activations Density 0.094%

    No Known Activations