© 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. 1-RES-JB
    11. 14353
    Prev
    Next
    INDEX
    Explanations

    references to students or pupils

    oai_token-act-pair · gpt-3.5-turbo

    references to students and their learning experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circumstance
    -0.73
     debilitating
    -0.65
     odds
    -0.64
     cumbersome
    -0.63
     deed
    -0.62
     melee
    -0.61
     normalized
    -0.60
     deeds
    -0.59
    MM
    -0.59
    ALTH
    -0.59
    POSITIVE LOGITS
     pupils
    1.30
     pupil
    1.28
    puff
    0.83
    uates
    0.83
    rentices
    0.80
    folios
    0.78
    flix
    0.77
    osate
    0.77
     Snape
    0.77
    glomer
    0.76
    Activations Density 0.007%

    No Known Activations