© 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. 22681
    Prev
    Next
    INDEX
    Explanations

    phrases related to directing the reader to additional information or actions on a webpage

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and references to menus or options within a document

    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
     inhib
    -0.66
    anooga
    -0.66
    cells
    -0.65
    ovo
    -0.65
     suppose
    -0.64
    iva
    -0.63
     tending
    -0.61
    conn
    -0.60
     guaranteeing
    -0.59
     itself
    -0.59
    POSITIVE LOGITS
     latest
    1.19
     aforementioned
    1.17
     same
    1.03
     following
    1.01
     widest
    1.01
     respective
    0.99
    ses
    0.94
     entirety
    0.91
     newest
    0.90
     nearest
    0.90
    Activations Density 0.426%

    No Known Activations