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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 17744
    Prev
    Next
    INDEX
    Explanations

    instances of the word "literally" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "literally" in various contexts

    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
    sonian
    -0.85
    lain
    -0.82
    ittal
    -0.79
     Horizon
    -0.75
    ies
    -0.74
    yright
    -0.69
    icipated
    -0.69
    lings
    -0.66
     Citiz
    -0.66
    )=(
    -0.65
    POSITIVE LOGITS
     piss
    0.74
    rely
    0.72
     engulf
    0.69
     fucking
    0.65
    Ń·
    0.65
    literally
    0.64
     outp
    0.64
     gra
    0.63
     hell
    0.62
    ãĤ§
    0.62
    Activations Density 0.023%

    No Known Activations