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. 19085
    Prev
    Next
    INDEX
    Explanations

    references to offers or the act of offering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "offer" and its variations

    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
     ancest
    -0.78
    cling
    -0.66
    icent
    -0.66
    lean
    -0.66
    mask
    -0.61
     habit
    -0.61
    error
    -0.60
     oxide
    -0.60
    carry
    -0.60
     aft
    -0.58
    POSITIVE LOGITS
    xual
    0.84
    BACK
    0.76
    backs
    0.75
     sheet
    0.72
    igslist
    0.71
    ings
    0.71
     expires
    0.71
     fulfilled
    0.71
    irection
    0.71
    ointment
    0.71
    Activations Density 0.031%

    No Known Activations