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. 0-RES-JB
    6. 8817
    Prev
    Next
    INDEX
    Explanations

    phrases where the term "literally" is used intensively

    oai_token-act-pair · gpt-3.5-turbo

    the word "literally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},{"
    -0.74
    ente
    -0.68
    "}],"
    -0.67
    fourth
    -0.66
    ieth
    -0.64
    isers
    -0.64
    "},"
    -0.62
    bour
    -0.61
    jl
    -0.60
     Differences
    -0.59
    POSITIVE LOGITS
     literally
    3.34
    literally
    2.63
     Literally
    2.30
     literal
    1.65
     basically
    1.58
     practically
    1.54
     essentially
    1.36
     figur
    1.27
     legitimately
    1.17
     honestly
    1.16
    Activations Density 0.018%

    No Known Activations