© 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. 10-RES-JB
    11. 18963
    Prev
    Next
    INDEX
    Explanations

    words posing questions or raising issues

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or questions about "the" and its associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icism
    -0.85
    cation
    -0.81
    matter
    -0.81
    leness
    -0.81
    iliation
    -0.80
    rama
    -0.80
    cture
    -0.79
    obook
    -0.79
    analysis
    -0.78
    hyde
    -0.77
    POSITIVE LOGITS
     indications
    1.16
     exceptions
    1.07
     signs
    1.06
     words
    1.04
     constants
    1.04
     truths
    1.00
     kinds
    0.99
     moments
    0.99
     nods
    0.98
     keys
    0.98
    Activations Density 0.176%

    No Known Activations