Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22958
    Prev
    Next
    INDEX
    Explanations

    lowercase single letter 't'

    oai_token-act-pair · gpt-3.5-turbo

    the letter "t"

    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
     Vie
    -0.73
     rounding
    -0.69
     nonex
    -0.66
     overtime
    -0.65
     Hitman
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     mortal
    -0.61
     Furious
    -0.60
     unwitting
    -0.60
     precedent
    -0.60
    POSITIVE LOGITS
    weet
    1.45
    utorial
    1.44
    ribune
    1.44
    itles
    1.37
    ournament
    1.31
    otally
    1.31
    uesday
    1.31
    urtle
    1.29
    ravis
    1.28
    alks
    1.26
    Activations Density 0.028%

    No Known Activations