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. 21256
    Prev
    Next
    INDEX
    Explanations

    phrases related to the company or brand "Hasbro."

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "Has" 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
    atically
    -0.68
    Interested
    -0.62
    osis
    -0.61
     glove
    -0.60
    ances
    -0.59
    eers
    -0.57
    ieri
    -0.57
     lining
    -0.56
    âĶĢâĶĢ
    -0.54
     dot
    -0.54
    POSITIVE LOGITS
    kell
    1.25
     been
    1.14
     Been
    1.12
    been
    1.07
     undergone
    1.04
    bro
    0.99
    bara
    0.96
    hed
    0.95
     Fallen
    0.93
     gotten
    0.90
    Activations Density 0.078%

    No Known Activations