© 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. 4-RES-JB
    6. 17296
    Prev
    Next
    INDEX
    Explanations

    mentions of technical terms related to web development and technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to the web and web technologies

    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
    terday
    -0.81
     unfocusedRange
    -0.78
    Downloadha
    -0.72
    士
    -0.71
    ++++++++++++++++
    -0.71
     retali
    -0.68
    ividual
    -0.67
    utherford
    -0.65
    uates
    -0.65
    ushima
    -0.64
    POSITIVE LOGITS
    inar
    1.00
     Browser
    0.92
     browsers
    0.92
    Socket
    0.91
    izen
    0.90
    Assembly
    0.88
    GL
    0.87
    cam
    0.84
    browser
    0.82
    iste
    0.81
    Activations Density 0.009%

    No Known Activations