© 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. 0-RES-JB
    11. 6533
    Prev
    Next
    INDEX
    Explanations

    words related to licensing and certification

    oai_token-act-pair · gpt-3.5-turbo

    references to licensed entities or professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mess
    -0.84
    atter
    -0.78
    message
    -0.70
    eat
    -0.70
    leaders
    -0.69
    atters
    -0.69
     hunger
    -0.69
    itiveness
    -0.68
     Defeat
    -0.68
    nuts
    -0.67
    POSITIVE LOGITS
     licensed
    3.83
     Licensed
    2.84
    licensed
    2.82
     licensing
    1.96
     licenses
    1.94
     licens
    1.89
    Lic
    1.88
     license
    1.88
     licensee
    1.85
     licences
    1.65
    Activations Density 0.018%

    No Known Activations