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. 7-RES-JB
    6. 9122
    Prev
    Next
    INDEX
    Explanations

    adverbs and words related to quantification or comparison

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that modify verbs or adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilater
    -0.79
    pie
    -0.79
    ulton
    -0.67
    axter
    -0.67
    oling
    -0.67
    natureconservancy
    -0.66
    schild
    -0.66
     vest
    -0.65
    abit
    -0.65
     treasure
    -0.63
    POSITIVE LOGITS
     Speaking
    0.79
     speaking
    0.76
     Sabha
    0.75
     Completed
    0.74
     Seeking
    0.71
     Alive
    0.71
     RELE
    0.69
     Controlled
    0.68
     tuned
    0.68
     Tire
    0.67
    Activations Density 0.057%

    No Known Activations