© 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. 10-RES-JB
    11. 8433
    Prev
    Next
    INDEX
    Explanations

    references to motor vehicles and related terms

    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
     Beg
    -0.73
     Suc
    -0.73
     Michaels
    -0.69
     Alibaba
    -0.69
     Forbidden
    -0.68
     Gould
    -0.67
     BET
    -0.67
     Aval
    -0.66
     Caesar
    -0.65
     Ming
    -0.65
    POSITIVE LOGITS
    cycle
    1.52
    bike
    1.41
    cycl
    1.38
    cycles
    1.29
    cade
    1.17
    ized
    1.14
    otor
    1.06
    ised
    1.05
    cars
    1.04
    home
    1.04
    Activations Density 0.017%

    No Known Activations