© 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. 11-RES-JB
    11. 13620
    Prev
    Next
    INDEX
    Explanations

    terms indicating successful validation or confirmation of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate effectiveness or success in proving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.74
    ertodd
    -0.72
    letal
    -0.71
    anyon
    -0.71
    VIDIA
    -0.68
    ulkan
    -0.67
    ussed
    -0.66
    avascript
    -0.66
    lished
    -0.65
    ription
    -0.65
    POSITIVE LOGITS
     invaluable
    1.20
     irresistible
    1.16
     resilient
    1.11
     fruitful
    1.10
     elusive
    1.09
     prophetic
    1.06
     ineffective
    1.05
     decisive
    1.02
     incapable
    1.01
     useful
    0.99
    Activations Density 0.056%

    No Known Activations