© 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. 0-RES-JB
    11. 13707
    Prev
    Next
    INDEX
    Explanations

    instances where a document mentions specific numeric quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "appointment" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilde
    -0.73
     Bee
    -0.70
     Grimm
    -0.65
     Wallace
    -0.64
     Chrome
    -0.63
     KR
    -0.63
     biology
    -0.62
     Darwin
    -0.62
     lur
    -0.62
     soc
    -0.61
    POSITIVE LOGITS
    oint
    4.81
    ointed
    3.20
    ointment
    2.66
    unction
    1.46
    uncture
    1.25
    unct
    1.09
    ople
    1.02
    ranch
    1.02
    acket
    0.96
    osition
    0.90
    Activations Density 0.010%

    No Known Activations