© 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. 3-RES-JB
    11. 14738
    Prev
    Next
    INDEX
    Explanations

    words related to programming languages and instructions for installing and configuring software

    oai_token-act-pair · gpt-3.5-turbo

    elements related to software installation and programming tutorials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.68
    stre
    -0.64
     curfew
    -0.62
    SPONSORED
    -0.61
    drug
    -0.61
     Faul
    -0.57
     Mour
    -0.56
     Newsp
    -0.56
    cffffcc
    -0.56
     NAACP
    -0.56
    POSITIVE LOGITS
     plugin
    0.99
     deprecated
    0.99
     backend
    0.97
     API
    0.92
     JSON
    0.90
     GitHub
    0.89
     initialization
    0.85
     api
    0.85
     debug
    0.85
     plugins
    0.84
    Activations Density 1.651%

    No Known Activations