© 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. 0-RES-JB
    6. 20098
    Prev
    Next
    INDEX
    Explanations

    technology-related words and functionalities that support specific features

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating endorsement or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arted
    -0.71
    iring
    -0.63
     Gone
    -0.60
    lot
    -0.60
    itty
    -0.59
    fried
    -0.58
     eternity
    -0.58
    gone
    -0.58
     whim
    -0.57
    hit
    -0.57
    POSITIVE LOGITS
     supports
    3.49
     Supports
    2.67
     support
    2.09
     supported
    2.04
     Support
    1.92
    support
    1.89
    Support
    1.83
     supporting
    1.78
     SUPPORT
    1.67
     opposes
    1.65
    Activations Density 0.008%

    No Known Activations