© 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. 9937
    Prev
    Next
    INDEX
    Explanations

    websites or texts containing the word "lic"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'lic' which typically relates to licensing or permits

    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
     Unch
    -0.76
    ħĭ
    -0.74
     Lans
    -0.72
    thing
    -0.69
     Ended
    -0.69
    izoph
    -0.69
     Everywhere
    -0.68
    skirts
    -0.68
     Samoa
    -0.66
     Panda
    -0.66
    POSITIVE LOGITS
    ensing
    1.47
    enses
    1.26
    hess
    1.23
    entious
    1.02
    ensable
    1.02
    ious
    1.01
    ences
    0.93
     acids
    0.93
    ensed
    0.93
    atable
    0.92
    Activations Density 0.021%

    No Known Activations