© 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. 16122
    Prev
    Next
    INDEX
    Explanations

    references to GitHub repositories and source code

    oai_token-act-pair · gpt-3.5-turbo

    references to GitHub and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    phe
    -0.83
    amina
    -0.80
    othing
    -0.73
    akening
    -0.70
     Robbins
    -0.70
     Glac
    -0.70
    IU
    -0.70
    iren
    -0.69
    lear
    -0.69
    lla
    -0.68
    POSITIVE LOGITS
     repository
    1.56
     repositories
    1.56
     repo
    1.38
     GitHub
    1.19
    usercontent
    1.17
     github
    1.11
     Github
    1.08
    github
    1.05
     Pages
    1.01
     wiki
    1.01
    Activations Density 0.061%

    No Known Activations