© 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 EvalsExportsAPI 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. 16935
    Prev
    Next
    INDEX
    Explanations

    assurances and statements conveying certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of assurance or promises

    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
    ynski
    -0.76
    adesh
    -0.73
    abouts
    -0.69
    isol
    -0.65
     sided
    -0.62
    ikes
    -0.61
    chery
    -0.60
    earable
    -0.59
     Includes
    -0.59
    artifacts
    -0.58
    POSITIVE LOGITS
     readers
    1.10
     anybody
    1.01
     anyone
    1.01
     thee
    1.01
     ya
    1.00
     listeners
    0.99
     you
    0.94
     viewers
    0.94
     myself
    0.92
     believers
    0.91
    Activations Density 0.106%

    No Known Activations