© 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. 6-RES-JB
    11. 9961
    Prev
    Next
    INDEX
    Explanations

    instances of the word "exercise" when associated with actions or rights

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of exercising rights and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agate
    -0.65
     Fritz
    -0.63
     Bangladesh
    -0.62
     oscill
    -0.62
     Rebels
    -0.61
     upstream
    -0.61
     Hindus
    -0.61
     Puzzles
    -0.60
     Italians
    -0.60
     Enterprises
    -0.59
    POSITIVE LOGITS
    luster
    0.87
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.84
    pter
    0.83
    ighth
    0.80
     newfound
    0.78
     dignity
    0.76
    pecially
    0.74
    raph
    0.74
    avorite
    0.73
    confidence
    0.72
    Activations Density 0.470%

    No Known Activations