© 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. 11-RES-JB
    11. 7654
    Prev
    Next
    INDEX
    Explanations

    holiday greetings or well-wishes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.72
    ensibly
    -0.70
    ascus
    -0.69
    ',"
    -0.68
     coerc
    -0.67
     clandestine
    -0.66
     challeng
    -0.66
     authorised
    -0.66
     torpedo
    -0.65
     disparate
    -0.65
    POSITIVE LOGITS
    âĢ
    1.68
     âĢ
    1.46
    ↵
    1.39
     ðŁĺ
    1.22
    <|endoftext|>
    1.16
     Anyway
    1.16
     âĻ
    1.15
     Wouldn
    1.11
     Regardless
    1.10
     However
    1.08
    Activations Density 0.398%

    No Known Activations