© 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. 1-RES-JB
    11. 20338
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atem
    -0.67
    çĭ
    -0.65
     Mills
    -0.62
     Stevenson
    -0.62
    arily
    -0.62
    ãģ®å®
    -0.62
    Ĩ
    -0.60
     Knife
    -0.59
     Manson
    -0.58
    ãģ®éŃĶ
    -0.57
    POSITIVE LOGITS
    -'
    0.92
    ËĪ
    0.91
    catentry
    0.86
    _-
    0.85
    ï¸
    0.81
    dayName
    0.81
    vernment
    0.80
    wcsstore
    0.78
    hesda
    0.74
    rongh
    0.72
    Activations Density 0.008%

    No Known Activations