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. 3362
    Prev
    Next
    INDEX
    Explanations

    names related to the word "Grease"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Gre."

    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
    amins
    -0.74
    ãĥŁ
    -0.71
    atari
    -0.70
    intendo
    -0.68
    ported
    -0.66
     CT
    -0.65
    iri
    -0.64
    Motor
    -0.63
    adiq
    -0.62
    CV
    -0.62
    POSITIVE LOGITS
     Gre
    3.90
    Gre
    2.93
    gre
    1.89
     gre
    1.62
     GRE
    1.30
     Gree
    1.22
     grease
    1.21
     Syri
    1.13
     Gra
    1.13
     Cle
    1.11
    Activations Density 0.016%

    No Known Activations