© 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. 9-RES-JB
    11. 10406
    Prev
    Next
    INDEX
    Explanations

    Unix/Linux file paths and commands

    oai_token-act-pair · gpt-3.5-turbo

    file paths and command line syntax

    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
     Beir
    -0.96
     Faul
    -0.79
     Grimm
    -0.73
     Coffin
    -0.72
     discriminating
    -0.70
     Gilbert
    -0.70
     Puzz
    -0.70
     CPC
    -0.70
     Hughes
    -0.69
     Morgan
    -0.69
    POSITIVE LOGITS
    usr
    1.62
    tmp
    1.58
    home
    1.50
    Users
    1.45
    Applications
    1.34
    proc
    1.33
    path
    1.30
    etc
    1.28
    root
    1.27
    var
    1.26
    Activations Density 0.031%

    No Known Activations