© 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. 20125
    Prev
    Next
    INDEX
    Explanations

    mentions of academic professionals or experts

    oai_token-act-pair · gpt-3.5-turbo

    references to academic titles, specifically 'Professor'

    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
     destro
    -0.87
    ãĥ¼ãĥ³
    -0.80
     queen
    -0.80
     takeoff
    -0.71
     annexed
    -0.69
    OPA
    -0.69
     sled
    -0.68
    TOR
    -0.67
     cruc
    -0.67
    aukee
    -0.66
    POSITIVE LOGITS
    essors
    1.11
     Puzz
    0.95
    ĨĴ
    0.90
     Laure
    0.87
     Professor
    0.85
     Michel
    0.83
    umin
    0.79
     emer
    0.78
     Lect
    0.78
     Dawkins
    0.76
    Activations Density 0.014%

    No Known Activations