© 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. 11290
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a revelation or admission of truth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Truth" and related concepts

    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
     Banner
    -0.65
    etsk
    -0.57
     carriage
    -0.56
     Settlement
    -0.53
     refugee
    -0.53
     Lyme
    -0.52
    ropolis
    -0.52
     segregation
    -0.52
    HOME
    -0.51
    election
    -0.51
    POSITIVE LOGITS
    cially
    1.26
    wise
    1.21
    ifully
    1.17
    pecially
    1.14
    identally
    1.08
    inarily
    1.05
    entimes
    1.05
    arily
    1.03
    entially
    1.03
    arently
    1.03
    Activations Density 0.289%

    No Known Activations