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. 8619
    Prev
    Next
    INDEX
    Explanations

    words related to dedication or commitment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dedication or commitmen

    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
     Circle
    -0.68
    oor
    -0.65
     patterns
    -0.63
    ira
    -0.61
    utra
    -0.58
     obsc
    -0.56
     whiff
    -0.56
     Markets
    -0.56
     grids
    -0.55
     Tate
    -0.55
    POSITIVE LOGITS
    ded
    4.81
    ding
    1.82
     Ded
    1.48
    ds
    1.28
    sed
    1.23
    med
    1.15
    ged
    1.12
    ted
    1.10
    der
    1.10
     deductible
    1.06
    Activations Density 0.013%

    No Known Activations