© 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. 4-RES-JB
    11. 2617
    Prev
    Next
    INDEX
    Explanations

    calls to action related to signing up for newsletters

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to newsletter sign-up

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.79
    ooked
    -0.72
    »Ĵ
    -0.71
    amily
    -0.66
    olt
    -0.65
    ĸļ
    -0.64
    prototype
    -0.63
     dwelling
    -0.62
    IRO
    -0.61
    ISION
    -0.61
    POSITIVE LOGITS
     Sign
    1.13
    ific
    1.09
    ificantly
    1.04
    atories
    1.02
    Sign
    0.98
    atory
    0.93
    atures
    0.88
    zai
    0.87
    ifying
    0.86
    ging
    0.86
    Activations Density 0.012%

    No Known Activations