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. 11-RES-JB
    6. 3275
    Prev
    Next
    INDEX
    Explanations

    the word "literally" used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "literally" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortunate
    -0.82
    lain
    -0.81
    OA
    -0.80
     sufficiently
    -0.75
    Generally
    -0.73
     reasonably
    -0.71
    oglu
    -0.70
    arters
    -0.69
    ately
    -0.69
    afa
    -0.69
    POSITIVE LOGITS
     overnight
    0.82
     begging
    0.80
     trillions
    0.76
     illiter
    0.74
     hundreds
    0.73
     thousands
    0.73
     begged
    0.72
     billions
    0.71
     speaking
    0.70
     eyeb
    0.69
    Activations Density 0.048%

    No Known Activations