© 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. 7-RES-JB
    11. 2198
    Prev
    Next
    INDEX
    Explanations

    keywords related to revitalizing or revitalization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to revitalization and community enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERA
    -0.82
    achu
    -0.80
    ring
    -0.73
    emaker
    -0.72
    ulate
    -0.70
    ollow
    -0.70
    hold
    -0.70
    ware
    -0.69
    rers
    -0.69
    Wilson
    -0.68
    POSITIVE LOGITS
    issance
    0.81
     nerv
    0.71
    uations
    0.69
     GOODMAN
    0.68
     revital
    0.68
    pelling
    0.68
     Ukrain
    0.68
    ````
    0.67
    ynam
    0.67
    ysis
    0.65
    Activations Density 0.122%

    No Known Activations