© 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. 2-RES-JB
    11. 17533
    Prev
    Next
    INDEX
    Explanations

    the word "Heritage" at various activation levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Heritage Foundation

    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
    redd
    -0.71
    agram
    -0.70
    tered
    -0.70
    orders
    -0.67
    vern
    -0.66
     unsub
    -0.66
    odiac
    -0.65
    gradient
    -0.65
    ching
    -0.65
    sie
    -0.63
    POSITIVE LOGITS
     Heritage
    1.16
    conservancy
    1.05
    itage
    0.89
     Foundation
    0.81
     Collection
    0.77
     Institutes
    0.74
    icity
    0.72
     Dictionary
    0.72
     Institute
    0.72
     Values
    0.71
    Activations Density 0.008%

    No Known Activations