© 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. 0-RES-JB
    6. 10457
    Prev
    Next
    INDEX
    Explanations

    references to files in PDF format

    oai_token-act-pair · gpt-3.5-turbo

    references to PDF documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stage
    -0.76
     superst
    -0.74
     constantly
    -0.73
     line
    -0.72
     fart
    -0.66
     every
    -0.65
     occupied
    -0.64
     station
    -0.64
     scene
    -0.64
     hom
    -0.64
    POSITIVE LOGITS
    pdf
    4.11
    PDF
    3.46
     pdf
    1.60
    htm
    1.26
    doc
    1.24
    mobi
    1.15
     PDF
    1.10
    DOC
    1.10
    Documents
    1.09
    emphasis
    1.09
    Activations Density 0.017%

    No Known Activations