© 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. 5651
    Prev
    Next
    INDEX
    Explanations

    phrases describing requirements or prerequisites

    oai_token-act-pair · gpt-3.5-turbo

    references to requirements or necessities in varying contexts

    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
    ocry
    -0.79
     Bye
    -0.72
    alde
    -0.70
    oday
    -0.69
    eared
    -0.67
    lez
    -0.66
    emies
    -0.66
    apor
    -0.65
    eden
    -0.64
    iane
    -0.64
    POSITIVE LOGITS
     careful
    1.04
     upfront
    0.99
     diligence
    0.96
     meticulous
    0.96
     expenditure
    0.93
     ingenuity
    0.91
     sacrifice
    0.90
     intervention
    0.89
     painstaking
    0.88
     commitment
    0.88
    Activations Density 0.178%

    No Known Activations