© 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. 2-RES-JB
    11. 6286
    Prev
    Next
    INDEX
    Explanations

    email addresses and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    email addresses or social media handles

    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
     produ
    -0.67
     Somers
    -0.65
     Zamb
    -0.62
     Elephant
    -0.62
     Clicker
    -0.62
     guided
    -0.61
    senal
    -0.61
     Reaper
    -0.60
     Sod
    -0.60
    oted
    -0.59
    POSITIVE LOGITS
    #$
    1.39
    gmail
    1.15
    yahoo
    1.00
    realDonaldTrump
    0.89
    email
    0.89
    wik
    0.89
    andy
    0.88
    groups
    0.87
    ls
    0.86
    mic
    0.84
    Activations Density 0.009%

    No Known Activations