© 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. 2-RES-JB
    11. 19734
    Prev
    Next
    INDEX
    Explanations

    references to maps

    oai_token-act-pair · gpt-3.5-turbo

    references to maps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nuts
    -0.89
    cellaneous
    -0.80
    icer
    -0.79
    vae
    -0.77
    aneous
    -0.75
    ntil
    -0.71
    weeney
    -0.71
    ente
    -0.70
    ruciating
    -0.70
    nder
    -0.70
    POSITIVE LOGITS
     map
    1.04
     maps
    0.89
    ographer
    0.86
     mapped
    0.85
    map
    0.81
     Map
    0.78
    ãĤº
    0.71
     mapping
    0.71
     outline
    0.71
     Operator
    0.70
    Activations Density 0.011%

    No Known Activations