© 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. 1-RES-JB
    11. 19333
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistency or conformity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "keeping."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUN
    -0.70
    Merit
    -0.69
    Interstitial
    -0.69
    ones
    -0.65
    emphasis
    -0.63
    çīĪ
    -0.62
     Dud
    -0.62
    NetMessage
    -0.61
    swick
    -0.60
     Dism
    -0.60
    POSITIVE LOGITS
     tabs
    0.95
     keeping
    0.85
    keeping
    0.84
     vigil
    0.83
     track
    0.82
     pace
    0.81
     alive
    0.71
     afloat
    0.71
     preserving
    0.70
     rall
    0.69
    Activations Density 0.010%

    No Known Activations