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. 12702
    Prev
    Next
    INDEX
    Explanations

    phrases related to inviting and sharing information in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "re."

    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
     à¨
    -0.77
    EStream
    -0.73
    ãħĭ
    -0.67
     HK
    -0.65
     Phar
    -0.65
     gag
    -0.64
    DragonMagazine
    -0.64
     Nicarag
    -0.63
     background
    -0.62
     teasp
    -0.61
    POSITIVE LOGITS
    versible
    1.05
    porter
    1.05
    apers
    0.94
    becca
    0.93
    uters
    0.92
    tera
    0.91
    anche
    0.90
    venue
    0.89
    acher
    0.89
    rence
    0.88
    Activations Density 0.058%

    No Known Activations