© 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. 5083
    Prev
    Next
    INDEX
    Explanations

    terms related to clever or skillful actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "trick" and its variants

    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
    ccording
    -0.73
    ankind
    -0.71
     isot
    -0.69
    vation
    -0.68
     Domain
    -0.67
    olars
    -0.67
     Supplement
    -0.64
     Expend
    -0.64
     enrichment
    -0.64
    ndum
    -0.64
    POSITIVE LOGITS
    ery
    1.21
    ster
    1.06
     tricks
    1.02
    eries
    0.96
     trick
    0.96
    aroo
    0.94
    sters
    0.93
     Trick
    0.88
    iest
    0.86
    door
    0.86
    Activations Density 0.023%

    No Known Activations