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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18763
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific band named "Muse."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of musical terms or references to music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Mus" or " Mus"

    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aval
    -0.72
     Breach
    -0.68
     Integ
    -0.67
     damned
    -0.67
     bye
    -0.62
     Moor
    -0.61
     Yamato
    -0.60
     Span
    -0.58
     Rossi
    -0.58
     Maxwell
    -0.57
    POSITIVE LOGITS
    icians
    1.25
    cular
    1.22
    ician
    1.20
    ket
    1.09
    sels
    1.08
    ique
    1.08
    cled
    1.08
    itionally
    1.07
    cul
    1.06
    pel
    1.04
    Activations Density 0.038%

    No Known Activations