© 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 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. 8-RES-JB
    11. 11053
    Prev
    Next
    INDEX
    Explanations

    references to bio-related terms such as biofuels, bioelectricity, biomaterials, etc

    oai_token-act-pair · gpt-3.5-turbo

    references to biofuels and bio-related energy sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NOTICE
    -0.72
    ership
    -0.71
    ynasty
    -0.68
     Parables
    -0.67
    UAL
    -0.67
    urat
    -0.66
    naire
    -0.65
     Revel
    -0.65
    inho
    -0.65
     Tripoli
    -0.64
    POSITIVE LOGITS
    hazard
    1.63
    fuel
    1.20
    engineering
    1.12
    ethical
    1.10
    availability
    1.07
    engine
    1.07
    electric
    1.06
    feed
    1.05
    char
    1.03
    film
    0.99
    Activations Density 0.023%

    No Known Activations