© 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. 23647
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong opinion or assessment of a situation

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting existence or evaluation of various subjects

    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
     retrie
    -0.73
    ievers
    -0.70
     rul
    -0.68
     exits
    -0.65
     conductor
    -0.64
    Introduced
    -0.64
    ventures
    -0.64
     lear
    -0.64
    arling
    -0.64
    iever
    -0.64
    POSITIVE LOGITS
     testament
    1.11
     laughable
    1.10
     understandable
    1.06
     unacceptable
    1.05
     certainly
    1.05
     ridiculous
    1.04
     hardly
    1.01
     astounding
    1.01
     akin
    1.01
     absurd
    1.00
    Activations Density 0.196%

    No Known Activations