© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 10103
    Prev
    Next
    INDEX
    Explanations

    phrases where the word "literally" is used

    oai_token-act-pair · gpt-3.5-turbo

    the word "literally" and its various usages

    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
    lain
    -0.84
    ression
    -0.75
    ittal
    -0.71
     Horizon
    -0.71
    OA
    -0.70
    oglu
    -0.70
    bourg
    -0.69
    ies
    -0.69
    ately
    -0.67
    winner
    -0.66
    POSITIVE LOGITS
     begging
    0.78
     begged
    0.77
     piss
    0.75
    ruciating
    0.73
     nowhere
    0.71
     trillions
    0.69
     eyeb
    0.69
    ciating
    0.67
     overnight
    0.67
     wiped
    0.67
    Activations Density 0.036%

    No Known Activations