© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 558
    Prev
    Next
    INDEX
    Explanations

    specific punctuations like periods to end sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain concluding statements or full stops

    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
     tyr
    -0.90
     condol
    -0.76
     metic
    -0.74
     silent
    -0.74
    uly
    -0.72
     redes
    -0.71
     reven
    -0.70
     defe
    -0.70
     forgot
    -0.70
     purse
    -0.70
    POSITIVE LOGITS
     Researchers
    1.21
     Moreover
    1.10
     Scientists
    1.08
     Additionally
    1.07
     Whereas
    1.06
     Furthermore
    1.05
     However
    1.04
     Typically
    1.03
     Ideally
    1.01
     Fortunately
    1.01
    Activations Density 0.736%

    No Known Activations