© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5793
    Prev
    Next
    INDEX
    Explanations

    incorrectly formatted or invalid email addresses

    oai_token-act-pair · gpt-3.5-turbo

    indicators of invalid email addresses and subscription prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.88
     [/
    -0.84
     favoring
    -0.73
    cius
    -0.73
    [/
    -0.73
     recognizing
    -0.71
     ["
    -0.69
     stabilize
    -0.69
    cellaneous
    -0.69
     [...]
    -0.69
    POSITIVE LOGITS
    Video
    0.90
     ITV
    0.76
     Pict
    0.73
    Liverpool
    0.72
     Tube
    0.69
     Portsmouth
    0.69
     Notting
    0.68
     DUP
    0.65
     CCTV
    0.65
    ())
    0.64
    Activations Density 0.137%

    No Known Activations