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. 8-RES-JB
    6. 17892
    Prev
    Next
    INDEX
    Explanations

    references to the beginning or start of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of an "opening" event, particularly in contexts related to performances, articles, or other formal beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieving
    -0.97
    tics
    -0.84
    rome
    -0.84
    rior
    -0.84
    ieve
    -0.80
    lean
    -0.78
    lete
    -0.78
    zin
    -0.77
    iever
    -0.77
    ikes
    -0.76
    POSITIVE LOGITS
     ceremonies
    1.05
     ceremony
    0.97
     weekend
    0.89
     Weekend
    0.84
     doors
    0.80
     Doors
    0.80
     rites
    0.80
     kickoff
    0.80
     salv
    0.79
     Hours
    0.79
    Activations Density 0.055%

    No Known Activations