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. 4-RES-JB
    6. 17995
    Prev
    Next
    INDEX
    Explanations

    actions or procedures that are typical, regular, or commonly performed

    oai_token-act-pair · gpt-3.5-turbo

    references to 'routine' activities or checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iva
    -0.72
    arag
    -0.71
     Falk
    -0.69
    oras
    -0.68
    avin
    -0.67
    ippi
    -0.67
    mented
    -0.67
    atchewan
    -0.66
    atorial
    -0.65
    onz
    -0.65
    POSITIVE LOGITS
     routine
    1.27
     routines
    1.13
     maintenance
    0.92
    outine
    0.84
     everyday
    0.74
    cffffcc
    0.73
     regimen
    0.73
     daily
    0.72
    motion
    0.71
    dayName
    0.69
    Activations Density 0.008%

    No Known Activations