© 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. 12330
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms within text, such as headings or sections of a document, with a pattern or structure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to guidance, recommendations, or instructions in various contexts

    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
     Zucker
    -0.67
    ociate
    -0.63
    )=(
    -0.63
    ulative
    -0.62
    imensional
    -0.61
    igmat
    -0.60
    enthal
    -0.60
    olis
    -0.58
    android
    -0.57
    686
    -0.57
    POSITIVE LOGITS
     Creatures
    0.71
     Again
    0.66
    ''.
    0.62
     Annotations
    0.60
    Lord
    0.59
     Telesc
    0.59
    prints
    0.58
     --------------------
    0.57
     Gle
    0.57
    Points
    0.56
    Activations Density 0.484%

    No Known Activations