© 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. 9-RES-JB
    11. 10116
    Prev
    Next
    INDEX
    Explanations

    comparisons or likelihoods of certain characteristics or behaviors between different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparative likelihoods or increases in probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    comings
    -0.90
    skirts
    -0.78
    rompt
    -0.73
     Lets
    -0.72
    ovie
    -0.71
    æ©
    -0.70
    adding
    -0.70
    facts
    -0.69
    agues
    -0.68
    agna
    -0.68
    POSITIVE LOGITS
     likely
    1.35
     than
    1.13
     prone
    1.07
    likely
    1.04
     susceptible
    1.03
     pronounced
    1.03
     Likely
    1.00
     prevalent
    0.98
     frequent
    0.97
     expensive
    0.95
    Activations Density 0.146%

    No Known Activations