© 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. 13695
    Prev
    Next
    INDEX
    Explanations

    titles of various creative works such as books, movies, comics, and series

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various forms of media and projects

    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
    ween
    -0.70
    ichever
    -0.67
     Roof
    -0.61
     fluids
    -0.59
    dfx
    -0.59
    afort
    -0.59
     Room
    -0.58
    gradient
    -0.58
    actionDate
    -0.57
    Textures
    -0.57
    POSITIVE LOGITS
     sorely
    0.76
     belongs
    0.76
     belong
    0.70
     represents
    0.66
     affiliate
    0.65
     demonstrates
    0.64
    eco
    0.63
     chain
    0.62
     foss
    0.60
     blat
    0.60
    Activations Density 0.299%

    No Known Activations