© 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. 2-RES-JB
    11. 8145
    Prev
    Next
    INDEX
    Explanations

    terms related to "reconciliation" or "reconfiguring"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reconnaissance or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Furious
    -0.72
    FORE
    -0.67
    TPS
    -0.66
     Gry
    -0.64
     Potter
    -0.64
     Hedge
    -0.64
     Jehovah
    -0.63
     Rowling
    -0.62
    Diamond
    -0.61
     Einstein
    -0.61
    POSITIVE LOGITS
    figured
    1.14
     recon
    1.06
    fig
    0.94
    vention
    0.93
    icol
    0.92
    verted
    0.92
    iqu
    0.92
    itial
    0.90
    cess
    0.87
    stant
    0.87
    Activations Density 0.007%

    No Known Activations