© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Museum" specifically in various texts

    oai_token-act-pair · gpt-3.5-turbo
    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
     Breach
    -0.75
     Aval
    -0.68
     damned
    -0.68
     Moor
    -0.63
     Integ
    -0.63
     bye
    -0.63
     Yamato
    -0.63
     Maxwell
    -0.60
     Ceres
    -0.59
     Veronica
    -0.59
    POSITIVE LOGITS
    icians
    1.32
    cular
    1.27
    ician
    1.25
    ket
    1.19
    cul
    1.15
    sels
    1.14
    cled
    1.12
    cle
    1.07
    cles
    1.06
    ique
    1.06
    Activations Density 0.024%

    No Known Activations