© 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. 1-RES-JB
    11. 2436
    Prev
    Next
    INDEX
    Explanations

    terms related to software, particularly those associated with GNU programs

    oai_token-act-pair · gpt-3.5-turbo

    references to specific software licenses and programming concepts

    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
    arat
    -0.94
    erb
    -0.86
    lyak
    -0.76
    asin
    -0.76
    illon
    -0.75
    asted
    -0.74
    onde
    -0.74
    holes
    -0.73
    anan
    -0.72
    ragon
    -0.72
    POSITIVE LOGITS
    tesy
    0.91
    kefeller
    0.82
    cery
    0.80
     Emacs
    0.78
     hiber
    0.74
    circ
    0.73
    uador
    0.73
    heed
    0.69
    stood
    0.67
     sul
    0.67
    Activations Density 0.020%

    No Known Activations