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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 1783
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maiden
    -0.68
     interrog
    -0.68
     marqu
    -0.66
    ihil
    -0.65
     multif
    -0.64
    aterasu
    -0.64
     princip
    -0.64
     clitor
    -0.63
    iqueness
    -0.63
     overcl
    -0.63
    POSITIVE LOGITS
     Photo
    1.69
     Courtesy
    1.54
     PHOTO
    1.52
     Photograph
    1.49
     Picture
    1.47
     Credit
    1.45
     REUTERS
    1.39
     Image
    1.36
     Photographer
    1.35
    Photo
    1.24
    Activations Density 0.654%

    No Known Activations