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. 5560
    Prev
    Next
    INDEX
    Explanations

    terms related to logic and reasoning

    oai_token-act-pair · gpt-3.5-turbo

    references to logic and reasoning

    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
    avez
    -0.74
     Volunte
    -0.71
    eded
    -0.71
    orks
    -0.67
    ription
    -0.66
    lain
    -0.66
    artney
    -0.65
     Leopard
    -0.65
     Rider
    -0.63
    emale
    -0.63
    POSITIVE LOGITS
     fallacy
    0.92
     logic
    0.91
    istically
    0.91
    matical
    0.89
     underpin
    0.88
     reasoning
    0.88
    istical
    0.85
     puzzles
    0.82
    otle
    0.78
    ical
    0.78
    Activations Density 0.046%

    No Known Activations