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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 8032
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "unsubstantiated"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "unsubstantiated."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    giving
    -0.73
    href
    -0.69
     marrow
    -0.69
    flix
    -0.67
    keeper
    -0.66
    jack
    -0.66
    worm
    -0.65
    keepers
    -0.63
     tender
    -0.63
    Frameworks
    -0.62
    POSITIVE LOGITS
    iated
    1.24
    ially
    1.08
    opoulos
    0.98
    iate
    0.97
    iating
    0.95
    iation
    0.93
    ricting
    0.89
    etric
    0.89
    imated
    0.88
    rons
    0.87
    Activations Density 0.019%

    No Known Activations