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. 1-RES-JB
    6. 12270
    Prev
    Next
    INDEX
    Explanations

    verbs related to expressions of consent or agreement

    oai_token-act-pair · gpt-3.5-turbo

    words related to representations and depictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.86
     NCT
    -0.77
    book
    -0.77
    books
    -0.74
    iege
    -0.68
    Anderson
    -0.67
    antage
    -0.67
    ãģ®ç
    -0.67
    Books
    -0.66
    illard
    -0.64
    POSITIVE LOGITS
    ented
    1.18
    reprene
    0.72
     vul
    0.72
    arthed
    0.71
    ropy
    0.70
    enting
    0.69
     piping
    0.67
    ents
    0.67
     fitt
    0.66
    ratulations
    0.65
    Activations Density 0.006%

    No Known Activations