Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 16661
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending in a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helper
    -0.78
     asylum
    -0.74
     salute
    -0.72
    interstitial
    -0.72
     allowance
    -0.71
     panc
    -0.70
     inner
    -0.69
     hourly
    -0.69
     tyr
    -0.68
     dich
    -0.65
    POSITIVE LOGITS
     Alternatively
    1.49
     Ideally
    1.38
     Regardless
    1.37
     Otherwise
    1.37
     Perhaps
    1.31
     Certainly
    1.30
     Depending
    1.29
     Especially
    1.28
     Instead
    1.28
     Either
    1.27
    Activations Density 0.716%

    No Known Activations