© 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. 10-RES-JB
    11. 16518
    Prev
    Next
    INDEX
    Explanations

    financial or transactional terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating completeness or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liest
    -0.83
    mere
    -0.67
     Tycoon
    -0.67
    tery
    -0.64
     Rou
    -0.64
    aceae
    -0.64
    gee
    -0.64
     Parables
    -0.63
     Mostly
    -0.63
     Passage
    -0.63
    POSITIVE LOGITS
    fledged
    1.05
     fled
    1.02
     clothed
    1.00
     stocked
    0.90
     functioning
    0.90
     utilized
    0.89
     immersed
    0.84
     realized
    0.84
     aware
    0.83
     embraced
    0.83
    Activations Density 0.030%

    No Known Activations