© 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. 15553
    Prev
    Next
    INDEX
    Explanations

    references to APIs

    oai_token-act-pair · gpt-3.5-turbo

    references to APIs

    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
    interest
    -0.84
    pard
    -0.83
    ners
    -0.82
     Gaia
    -0.80
    lihood
    -0.80
    lo
    -0.80
    pend
    -0.75
    fur
    -0.75
    wind
    -0.74
    mington
    -0.71
    POSITIVE LOGITS
    API
    0.97
     API
    0.92
    KEN
    0.83
     endpoint
    0.82
    URI
    0.80
    istry
    0.79
     APIs
    0.78
    YP
    0.77
     api
    0.73
     gateway
    0.73
    Activations Density 0.010%

    No Known Activations