© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5182
    Prev
    Next
    INDEX
    Explanations

    words related to technology and engineering, especially focusing on mechanisms and components

    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
     Scholar
    -0.76
     Violence
    -0.75
    FA
    -0.74
     apology
    -0.74
     Bye
    -0.72
     Anniversary
    -0.72
     Disorder
    -0.69
     vulgar
    -0.67
    Border
    -0.67
     Trends
    -0.67
    POSITIVE LOGITS
     coils
    1.18
     mounted
    1.17
     actu
    1.15
     coil
    1.15
     electrom
    1.14
     protr
    1.12
     electrodes
    1.11
     pumps
    1.09
     rotating
    1.04
    mounted
    1.04
    Activations Density 0.392%

    No Known Activations