© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19058
    Prev
    Next
    INDEX
    Explanations

    references to various types and uses of paper materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to materials made of paper

    oai_token-act-pair · gpt-3.5-turbo
    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
    hov
    -0.99
    oÄŁ
    -0.89
    EStreamFrame
    -0.76
    ctuary
    -0.75
    lvl
    -0.74
    zinski
    -0.71
    cius
    -0.71
    undai
    -0.70
    ETF
    -0.70
    iets
    -0.70
    POSITIVE LOGITS
     printer
    1.16
    clip
    1.13
     printers
    1.11
     printing
    1.11
     scissors
    1.08
     typew
    1.08
     ink
    1.06
     sheets
    1.06
     parchment
    1.03
     photoc
    1.03
    Activations Density 0.163%

    No Known Activations