© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17154
    Prev
    Next
    INDEX
    Explanations

    words related to tramplings or physical compression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tram" and its variations, along with related physical actions or effects

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

    No Comments

    Negative Logits
    FontSize
    -0.68
    iator
    -0.66
     populous
    -0.59
    arters
    -0.58
     independents
    -0.58
     magnification
    -0.58
     Governors
    -0.57
    Submit
    -0.57
    Friend
    -0.56
     Typhoon
    -0.56
    POSITIVE LOGITS
    pling
    1.46
    pled
    1.17
    plings
    1.03
    bley
    1.00
    pler
    0.96
    itual
    0.93
    imet
    0.86
    irez
    0.86
     tram
    0.85
    ãĥ¼ãĥ
    0.81
    Activations Density 0.008%

    No Known Activations