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. 9-RES-JB
    6. 20513
    Prev
    Next
    INDEX
    Explanations

    dialogues or statements made by someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said" and its variations, indicating reported speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sie
    -0.70
    hook
    -0.69
    born
    -0.68
    Lens
    -0.68
    eps
    -0.67
    pee
    -0.67
     Tradable
    -0.66
    actly
    -0.65
    Recipe
    -0.65
    Advertisements
    -0.65
    POSITIVE LOGITS
     furthermore
    1.00
     moreover
    0.97
     secondly
    0.79
     therefore
    0.70
     examples
    0.68
     however
    0.68
     although
    0.66
     there
    0.66
    adays
    0.66
     noting
    0.63
    Activations Density 0.189%

    No Known Activations