© 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. 23171
    Prev
    Next
    INDEX
    Explanations

    references to document formatting and structure

    oai_token-act-pair · gpt-3.5-turbo

    elements related to document or data formatting

    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
    roma
    -0.93
    doms
    -0.84
    arma
    -0.77
    ĺħ
    -0.73
    guard
    -0.72
    vironment
    -0.71
    interstitial
    -0.70
    adows
    -0.70
    nee
    -0.69
    minent
    -0.68
    POSITIVE LOGITS
    ters
    1.07
    ting
    0.98
    aldehyde
    0.82
     format
    0.81
    tered
    0.81
    atted
    0.78
    tering
    0.78
    ted
    0.76
    etter
    0.75
     formats
    0.75
    Activations Density 0.032%

    No Known Activations