© 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. 11418
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a statement or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest the existence or presence of certain subjects or situations

    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
    strom
    -0.65
     VIDEOS
    -0.63
     Savings
    -0.63
     Later
    -0.61
     Sources
    -0.61
     Him
    -0.61
     Cars
    -0.60
    ãĥŁ
    -0.60
    gur
    -0.59
    ãĥ©ãĥ³
    -0.59
    POSITIVE LOGITS
     ought
    0.97
     qualifies
    0.94
     satisfies
    0.93
     deserves
    0.92
     resembles
    0.90
     could
    0.90
     deserve
    0.88
     distinguishes
    0.88
     compares
    0.87
     corresponds
    0.86
    Activations Density 0.191%

    No Known Activations