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. 8-RES-JB
    6. 21333
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific celebrity named "Caboclo"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Cab" or "caboose" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iful
    -0.67
    ying
    -0.67
     cf
    -0.64
     Freddy
    -0.63
     clothes
    -0.61
    umeric
    -0.59
    pas
    -0.59
     Peb
    -0.58
    arily
    -0.58
    faces
    -0.58
    POSITIVE LOGITS
    raltar
    1.01
    arella
    0.89
    aret
    0.89
    lat
    0.84
    ris
    0.81
    xon
    0.81
    lished
    0.81
    isco
    0.81
    rik
    0.80
    bed
    0.79
    Activations Density 0.025%

    No Known Activations