© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic titles and institutions

    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
     labeling
    -1.04
     unfavorable
    -1.01
    colored
    -1.00
     favorable
    -0.90
     labeled
    -0.89
     favor
    -0.87
     favorably
    -0.85
    CLOSE
    -0.84
     favors
    -0.82
     victimized
    -0.82
    POSITIVE LOGITS
     Edinburgh
    1.59
     Cardiff
    1.57
     NHS
    1.54
     maths
    1.39
     £
    1.37
     Leicester
    1.35
     Leeds
    1.33
     Newcastle
    1.33
     UK
    1.32
     Sussex
    1.31
    Activations Density 0.235%

    No Known Activations