© 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. 11-RES-JB
    11. 3355
    Prev
    Next
    INDEX
    Explanations

    descriptions related to various disciplines or areas of study

    oai_token-act-pair · gpt-3.5-turbo

    positive descriptors related to activities and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Trooper
    -0.67
     backups
    -0.67
     Faw
    -0.67
     Ezekiel
    -0.66
    çļ
    -0.66
    payers
    -0.66
    äºĶ
    -0.66
     Pigs
    -0.66
    ivan
    -0.64
     sidx
    -0.64
    POSITIVE LOGITS
     genre
    1.49
     disciplines
    1.49
     genres
    1.42
     profession
    1.39
     sciences
    1.39
     discipline
    1.38
     topic
    1.37
     area
    1.34
     fields
    1.33
     field
    1.32
    Activations Density 0.473%

    No Known Activations