© 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. 3-RES-JB
    11. 17886
    Prev
    Next
    INDEX
    Explanations

    instructions or guides on how to do something

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guidelines beginning with "how to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nin
    -0.66
     poppy
    -0.62
    Cho
    -0.62
     Gupta
    -0.62
     Appears
    -0.61
    pants
    -0.60
    lights
    -0.60
    Mur
    -0.60
     FINAL
    -0.59
     costing
    -0.58
    POSITIVE LOGITS
     treat
    1.10
     conserve
    1.09
     keep
    1.08
     emulate
    1.07
     maximize
    1.07
     behave
    1.06
     give
    1.04
     reproduce
    1.02
     incorporate
    1.02
     communicate
    1.00
    Activations Density 0.308%

    No Known Activations