Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14889
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions related to trams or trampling

    oai_token-act-pair · gpt-3.5-turbo

    words related to public transport, specifically trams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.64
    FontSize
    -0.63
     magnification
    -0.62
    hift
    -0.60
     Governors
    -0.60
    EAR
    -0.59
    hots
    -0.58
    arters
    -0.58
     Goals
    -0.58
    HOME
    -0.58
    POSITIVE LOGITS
    pling
    1.33
    pled
    1.07
    bley
    1.04
    itual
    0.95
    irez
    0.91
    plings
    0.90
    puter
    0.88
    pler
    0.85
    ajo
    0.84
    ibur
    0.84
    Activations Density 0.004%

    No Known Activations