© 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. 4239
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or events

    oai_token-act-pair · gpt-3.5-turbo
    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
    ibr
    -0.75
    Tweet
    -0.70
    akra
    -0.65
    jar
    -0.64
    je
    -0.64
    deb
    -0.63
    paper
    -0.63
    umar
    -0.63
    tal
    -0.63
    ib
    -0.63
    POSITIVE LOGITS
    all
    1.47
     all
    1.38
     ALL
    1.38
    All
    1.20
     All
    1.18
    ALL
    1.13
     none
    1.06
     everything
    1.05
     entirety
    1.01
     EVERY
    1.00
    Activations Density 0.260%

    No Known Activations