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. 3-RES-JB
    6. 10474
    Prev
    Next
    INDEX
    Explanations

    people or terms related to the name "Alcide"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms, particularly related to individuals and cultural concepts

    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
    nesday
    -0.87
    ulhu
    -0.86
    ieval
    -0.85
    deen
    -0.83
    soDeliveryDate
    -0.82
    sylvania
    -0.80
    neys
    -0.79
    hips
    -0.78
    @#&
    -0.78
    ertodd
    -0.78
    POSITIVE LOGITS
     Alc
    0.76
    ides
    0.72
     brav
    0.69
    sts
    0.67
    Sov
    0.66
    Cu
    0.65
    bum
    0.63
     Quint
    0.63
     slee
    0.62
    Äį
    0.62
    Activations Density 0.016%

    No Known Activations