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. 19128
    Prev
    Next
    INDEX
    Explanations

    instances where the word "too" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "too" and its variations in context

    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
    anium
    -0.75
    ahime
    -0.72
    auri
    -0.70
    ptives
    -0.69
     Cosponsors
    -0.69
    urat
    -0.68
    hab
    -0.67
    culosis
    -0.66
    pires
    -0.66
    itiz
    -0.65
    POSITIVE LOGITS
    .:
    0.69
     congr
    0.69
     apologies
    0.67
    !:
    0.67
     forgive
    0.64
    .,
    0.64
     though
    0.63
     apologize
    0.62
     unintentional
    0.61
     pardon
    0.61
    Activations Density 0.186%

    No Known Activations