© 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. 18923
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-improvement or self-optimization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to missed opportunities or failures

    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
     Stamp
    -0.71
    iasis
    -0.63
    vil
    -0.63
     Bane
    -0.62
     bribe
    -0.62
     nails
    -0.61
     Tunnel
    -0.61
     Trent
    -0.59
     Customs
    -0.59
     ransom
    -0.59
    POSITIVE LOGITS
    ONSORED
    1.06
    icka
    0.83
     Byrd
    0.69
    +++
    0.68
    Args
    0.67
    olves
    0.65
    insky
    0.63
    etsk
    0.60
     McCartney
    0.60
    kernel
    0.59
    Activations Density 0.000%

    No Known Activations