© 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. 12-RES-JB
    11. 4079
    Prev
    Next
    INDEX
    Explanations

    scientific or technical descriptions related to containment or cooling systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to scientific concepts related to vacuum and thermodynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.77
     Disability
    -0.69
    arak
    -0.69
     Riders
    -0.68
    PDATE
    -0.67
    endas
    -0.66
    ploma
    -0.66
    resa
    -0.65
     redes
    -0.65
    intend
    -0.65
    POSITIVE LOGITS
     liquid
    1.61
     liquids
    1.60
     vapor
    1.49
     helium
    1.46
     molecules
    1.44
     molten
    1.38
     gases
    1.38
     atoms
    1.35
     fluids
    1.34
     visc
    1.31
    Activations Density 0.334%

    No Known Activations