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. 20807
    Prev
    Next
    INDEX
    Explanations

    words related to awakening or becoming active

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aw"

    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
     Prelude
    -0.69
     prelim
    -0.69
     MSM
    -0.69
     prol
    -0.68
     counters
    -0.62
     methyl
    -0.60
     Latino
    -0.60
     singles
    -0.59
     Strat
    -0.59
     STR
    -0.59
    POSITIVE LOGITS
    aw
    4.32
    aws
    2.68
    awed
    2.67
    awatts
    1.90
    AW
    1.88
    awa
    1.59
    awk
    1.49
    awar
    1.45
    awan
    1.42
    awi
    1.41
    Activations Density 0.016%

    No Known Activations