© 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. 11-RES-JB
    11. 7150
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms or people's names starting with "Str"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.69
     secrecy
    -0.63
     pleas
    -0.61
    eers
    -0.61
     Reeves
    -0.59
     hypers
    -0.58
     Garland
    -0.57
     Derby
    -0.57
    eer
    -0.57
     courts
    -0.57
    POSITIVE LOGITS
    ategy
    1.59
    ategic
    1.51
    ateg
    1.44
    anded
    1.39
    angers
    1.34
    atton
    1.33
    icken
    1.30
    ife
    1.25
    aditional
    1.23
    ained
    1.21
    Activations Density 0.022%

    No Known Activations