© 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. 13760
    Prev
    Next
    INDEX
    Explanations

    verbs relating to identifying or distinguishing between things

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to perception and distinguishing differences

    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
    forth
    -0.72
    ugal
    -0.69
    jet
    -0.66
    Contents
    -0.66
    illac
    -0.66
    assi
    -0.65
    mitted
    -0.64
    ciplinary
    -0.61
    rette
    -0.59
    ulic
    -0.59
    POSITIVE LOGITS
     apart
    1.09
    tale
    0.95
     whether
    0.94
     difference
    0.89
     anecd
    0.86
     if
    0.82
    whether
    0.81
     definitively
    0.75
     between
    0.71
     differences
    0.69
    Activations Density 0.063%

    No Known Activations