© 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. 11-RES-JB
    11. 3468
    Prev
    Next
    INDEX
    Explanations

    words related to growth and change

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to dynamics and changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Logged
    -0.74
    oning
    -0.72
    oof
    -0.67
    inently
    -0.67
    bies
    -0.63
     Quote
    -0.63
     Administration
    -0.62
    ointed
    -0.62
    asking
    -0.62
    cedented
    -0.62
    POSITIVE LOGITS
     prosper
    1.36
     flourish
    1.21
     evolve
    1.19
     thrive
    1.16
     evolves
    1.11
     decay
    1.10
     prolifer
    1.08
     thri
    1.07
     deterior
    1.04
     grows
    1.02
    Activations Density 0.120%

    No Known Activations