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. 2397
    Prev
    Next
    INDEX
    Explanations

    terms related to botanical taxonomy, specifically the word "genus"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological classification, particularly genus names and their properties

    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
     unden
    -0.69
    OUT
    -0.68
    addon
    -0.66
    oub
    -0.66
    outs
    -0.66
    immer
    -0.65
    isers
    -0.64
    psey
    -0.64
    blogs
    -0.63
    sticks
    -0.63
    POSITIVE LOGITS
     genus
    1.09
    eus
    0.85
     Amph
    0.80
     Species
    0.79
    aceae
    0.78
    cules
    0.74
     Priority
    0.73
     Vegeta
    0.72
     Homo
    0.72
     Ples
    0.70
    Activations Density 0.023%

    No Known Activations