© 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. 9-RES-JB
    11. 9922
    Prev
    Next
    INDEX
    Explanations

    short phrases or keywords containing the word "about."

    oai_token-act-pair · gpt-3.5-turbo

    sections that introduce or describe various topics or subjects

    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
    ãģ®ç
    -0.75
    BT
    -0.75
    ossal
    -0.65
    estyles
    -0.65
    ignt
    -0.64
    TRY
    -0.64
    Ùĩ
    -0.64
    PT
    -0.62
    ãĥı
    -0.61
    roads
    -0.61
    POSITIVE LOGITS
     Us
    1.06
     Languages
    0.77
     References
    0.75
     Paste
    0.74
     Author
    0.67
     Comments
    0.66
     Me
    0.66
     Yourself
    0.66
     Shots
    0.65
     halfway
    0.64
    Activations Density 0.035%

    No Known Activations