© 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. 3-RES-JB
    11. 16095
    Prev
    Next
    INDEX
    Explanations

    phrases or words that include the root "lic" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    terms related to licensing and permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.84
     Unch
    -0.80
     Lans
    -0.76
     Rabbit
    -0.72
     Samoa
    -0.67
     Everywhere
    -0.66
    skirts
    -0.66
     Whale
    -0.62
     Valkyrie
    -0.61
     Siber
    -0.61
    POSITIVE LOGITS
    ensing
    1.37
    enses
    1.13
    hess
    1.09
    ensable
    1.04
    ious
    0.96
    ensor
    0.95
    lic
    0.91
    entious
    0.90
    orrect
    0.89
    ensed
    0.88
    Activations Density 0.009%

    No Known Activations