© 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. 22011
    Prev
    Next
    INDEX
    Explanations

    prepositions combined with locations or descriptions of spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to urban areas and city dynamics

    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
    arcity
    -0.94
    jri
    -0.92
    zee
    -0.79
    apest
    -0.73
    idays
    -0.72
    ammy
    -0.72
    ĵĺ
    -0.71
    itual
    -0.70
    llor
    -0.68
    atonin
    -0.68
    POSITIVE LOGITS
    å°Ĩ
    0.83
     confines
    0.72
     cavern
    0.71
     pockets
    0.69
    士
    0.67
     bounds
    0.67
     scope
    0.66
     labyrinth
    0.65
    âĸ¬
    0.65
     lens
    0.62
    Activations Density 0.209%

    No Known Activations