© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 23822
    Prev
    Next
    INDEX
    Explanations

    phrases related to options or choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of conditionality or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cade
    -0.81
    interstitial
    -0.79
    Eva
    -0.73
    Motion
    -0.69
    hooting
    -0.67
    wikipedia
    -0.67
    handled
    -0.64
    iple
    -0.61
     Cyp
    -0.60
    due
    -0.60
    POSITIVE LOGITS
     worry
    1.19
     anymore
    1.12
     bother
    0.97
     wait
    0.85
     sacrifice
    0.80
     fret
    0.79
    oppers
    0.77
     settle
    0.77
     declare
    0.75
     resort
    0.73
    Activations Density 0.075%

    No Known Activations