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. 11984
    Prev
    Next
    INDEX
    Explanations

    names of individuals starting with the letter "j"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'j' in various contexts

    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
     subsistence
    -0.69
     Capitals
    -0.68
     outgoing
    -0.68
     dispers
    -0.67
     Carrier
    -0.66
     Scotia
    -0.66
     Siberian
    -0.65
     prolific
    -0.62
     TSA
    -0.62
     EntityItem
    -0.62
    POSITIVE LOGITS
    itsu
    1.31
    ournals
    1.30
    ordan
    1.21
    acket
    1.17
    ealous
    1.14
    ij
    1.13
    unction
    1.12
    utsu
    1.11
    ades
    1.10
    ade
    1.07
    Activations Density 0.016%

    No Known Activations