© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20617
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming languages and technical jargon

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of imaging or programmatic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DOJ
    -0.64
     unintentional
    -0.63
     prevailing
    -0.61
     Applicant
    -0.60
     occupational
    -0.60
     Univ
    -0.59
     Rapp
    -0.59
     selective
    -0.58
     exception
    -0.58
     WH
    -0.57
    POSITIVE LOGITS
    ogram
    1.46
    metry
    1.20
    ograms
    1.14
    matically
    1.09
    matical
    1.08
    raphic
    1.05
    rogram
    0.96
    matic
    0.95
    raph
    0.95
    naire
    0.94
    Activations Density 0.009%

    No Known Activations