© 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. 10-RES-JB
    11. 11295
    Prev
    Next
    INDEX
    Explanations

    computer-generated text formatting commands

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bengal
    -0.70
     board
    -0.69
     library
    -0.68
     Bris
    -0.66
     Droid
    -0.64
     Sapphire
    -0.62
     blanket
    -0.62
     detached
    -0.62
     playbook
    -0.61
     fid
    -0.61
    POSITIVE LOGITS
    Ĵ
    1.32
    ¹
    1.26
    ª
    1.24
    IJ
    1.21
    ı
    1.19
    ł
    1.17
    ij
    1.15
    «
    1.11
    ³
    1.10
    Į
    1.08
    Activations Density 0.157%

    No Known Activations