© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedures or actions being described

    oai_token-act-pair · gpt-3.5-turbo

    various forms of media and artistic expressions

    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
    bledon
    -0.85
    most
    -0.74
    wu
    -0.70
    wcs
    -0.68
    ivot
    -0.66
    forces
    -0.65
     carbohyd
    -0.64
    β
    -0.63
    ldon
    -0.63
    negie
    -0.63
    POSITIVE LOGITS
     depicting
    1.03
     poem
    0.90
     Generator
    0.90
     snippets
    0.90
     illustrating
    0.89
    writer
    0.87
     snippet
    0.84
     format
    0.82
     detailing
    0.82
     aloud
    0.81
    Activations Density 0.257%

    No Known Activations