© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 4810
    Prev
    Next
    INDEX
    Explanations

    references to the state of Massachusetts and the Massachusetts Institute of Technology (MIT)

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Massachusetts and its institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    pter
    -0.77
     FML
    -0.68
    loading
    -0.66
    cember
    -0.65
    loads
    -0.63
    arding
    -0.63
     totem
    -0.62
    stanbul
    -0.62
    utm
    -0.62
    arity
    -0.62
    POSITIVE LOGITS
    achusetts
    1.08
    achus
    0.95
     Bay
    0.91
     Lowell
    0.86
     Yard
    0.81
    Bay
    0.79
     lobster
    0.78
    heastern
    0.77
     Massachusetts
    0.77
    insula
    0.77
    Activations Density 0.075%

    No Known Activations