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. 10-RES-JB
    6. 15527
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up for various programs, services, or agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sign" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gypt
    -0.78
    »Ĵ
    -0.75
    negie
    -0.68
    âĨij
    -0.67
    ĸļ
    -0.66
    bsite
    -0.65
    regate
    -0.61
    ricular
    -0.61
     marrow
    -0.60
    ctory
    -0.58
    POSITIVE LOGITS
    atories
    1.10
     agreements
    1.06
     affidav
    1.01
    alled
    1.00
     petitions
    0.99
    ificantly
    0.99
     waivers
    0.98
     contracts
    0.95
     confidentiality
    0.90
    ATURES
    0.90
    Activations Density 0.035%

    No Known Activations