© 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. 4-RES-JB
    11. 17360
    Prev
    Next
    INDEX
    Explanations

    technical terms or acronyms related to computer science, such as 'CI' and 'Lisp'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific identifiers and acronyms, particularly "CI."

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

    No Comments

    Negative Logits
    sburg
    -1.03
    wagen
    -0.95
    andowski
    -0.85
    ding
    -0.82
    spread
    -0.80
    loads
    -0.80
    boards
    -0.79
    load
    -0.78
    side
    -0.77
    eting
    -0.77
    POSITIVE LOGITS
    CI
    0.86
     competence
    0.79
    ourage
    0.78
    KE
    0.78
    oglu
    0.78
     CI
    0.77
    PS
    0.74
    ANCE
    0.73
    UTION
    0.73
    xual
    0.72
    Activations Density 0.013%

    No Known Activations