© 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. 3-RES-JB
    11. 21241
    Prev
    Next
    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hilary" and related discussions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¹
    -0.75
     Izan
    -0.74
    Ħ¢
    -0.69
    EED
    -0.67
     disperse
    -0.67
    --------------------------------------------------------
    -0.66
    NetMessage
    -0.66
    âĸ¬
    -0.66
     Horses
    -0.62
     Powerful
    -0.62
    POSITIVE LOGITS
     Hil
    0.94
    iday
    0.90
    glers
    0.88
    uca
    0.87
    umin
    0.87
    ary
    0.86
    ims
    0.84
    ux
    0.83
    rite
    0.83
    aires
    0.82
    Activations Density 0.017%

    No Known Activations