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. 10471
    Prev
    Next
    INDEX
    Explanations

    mentions or references to muscular activities or body parts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to music

    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
     Incarnation
    -0.65
    agher
    -0.64
     Chrys
    -0.63
     century
    -0.61
     Thousand
    -0.60
     Hundred
    -0.60
     Dull
    -0.59
    sets
    -0.57
     Rabbit
    -0.57
     Creep
    -0.57
    POSITIVE LOGITS
    mus
    1.28
    achus
    1.03
    cled
    0.97
    cular
    0.95
    ierrez
    0.95
    andise
    0.94
    cles
    0.92
    cling
    0.92
    cle
    0.90
    cules
    0.85
    Activations Density 0.004%

    No Known Activations