© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 9561
    Prev
    Next
    INDEX
    Explanations

    programming code syntax related to arrows and variable assignment

    oai_token-act-pair · gpt-3.5-turbo

    symbols and operators used in programming or code functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enthal
    -0.93
    rahim
    -0.76
    mble
    -0.76
    restling
    -0.74
    ancies
    -0.72
    ament
    -0.72
    enance
    -0.72
    isf
    -0.71
    soDeliveryDate
    -0.71
    Gamer
    -0.71
    POSITIVE LOGITS
    ²¾
    0.71
     IO
    0.71
     Destination
    0.66
     Chr
    0.65
     Mongolia
    0.63
    flags
    0.63
     Register
    0.63
     justify
    0.63
    OOL
    0.63
     crops
    0.61
    Activations Density 0.012%

    No Known Activations