© 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. 2909
    Prev
    Next
    INDEX
    Explanations

    references to significant events or changes over time

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases indicating change or comparison

    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
     Secondly
    -0.70
     libel
    -0.61
    endez
    -0.61
    Secondly
    -0.59
     endors
    -0.57
    oros
    -0.56
    ribed
    -0.56
    liner
    -0.55
     rapists
    -0.55
     Sapp
    -0.54
    POSITIVE LOGITS
     anew
    0.93
     renewed
    0.84
     periodically
    0.79
     newer
    0.78
    peat
    0.78
     aging
    0.78
     milestones
    0.77
    uberty
    0.76
     rebirth
    0.75
     finally
    0.74
    Activations Density 1.063%

    No Known Activations