© 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. 4-RES-JB
    11. 1224
    Prev
    Next
    INDEX
    Explanations

    words related to computer science or abbreviations related to CS courses

    oai_token-act-pair · gpt-3.5-turbo

    references to computer science classes or coursework

    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
    ously
    -0.77
    accompan
    -0.70
    iqueness
    -0.70
     persu
    -0.67
     htt
    -0.62
     indebted
    -0.62
    Reviewer
    -0.62
    edged
    -0.62
    accompanied
    -0.61
     Mandela
    -0.61
    POSITIVE LOGITS
    IRO
    1.02
    GO
    0.97
    ANE
    0.94
    MC
    0.92
    DF
    0.91
    RF
    0.90
    DP
    0.90
    RL
    0.88
    IS
    0.87
    GL
    0.85
    Activations Density 0.009%

    No Known Activations