© 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 EvalsExportsinterp-engineNEWAPI 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. 18781
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical information or services, like specialized screen repair companies and development applications

    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
     honored
    -1.04
     favored
    -0.96
     favorably
    -0.95
     favors
    -0.95
     favoring
    -0.93
     honors
    -0.92
     favor
    -0.91
     honoring
    -0.90
     traveling
    -0.86
     utilized
    -0.85
    POSITIVE LOGITS
    Labour
    1.39
     £
    1.33
    £
    1.31
    Britain
    1.29
     Whilst
    1.28
    Scotland
    1.27
    BBC
    1.24
     Labour
    1.21
    England
    1.20
    Liverpool
    1.17
    Activations Density 0.466%

    No Known Activations