© 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. 7175
    Prev
    Next
    INDEX
    Explanations

    sections of text related to legal codes and regulations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings

    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
     tremend
    -0.75
    ikuman
    -0.72
     rall
    -0.70
     metic
    -0.68
     resisted
    -0.68
     butcher
    -0.68
     neighb
    -0.68
     board
    -0.67
    ding
    -0.67
     pit
    -0.67
    POSITIVE LOGITS
    aspx
    0.90
    Downloadha
    0.84
     Afterwards
    0.84
     Retrieved
    0.84
    blogspot
    0.82
     Additionally
    0.81
     Similarly
    0.80
    olson
    0.80
     Alternatively
    0.80
    htm
    0.80
    Activations Density 0.076%

    No Known Activations