© 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. 22531
    Prev
    Next
    INDEX
    Explanations

    references to physical objects or concepts related to sliding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports rules and player safety

    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
    ashtra
    -0.70
    auldron
    -0.67
    ronic
    -0.67
    cially
    -0.67
     Franch
    -0.65
     Pryor
    -0.64
    erva
    -0.64
     Petr
    -0.64
    ername
    -0.63
     manufacture
    -0.63
    POSITIVE LOGITS
     slides
    2.75
     flats
    2.00
     attendees
    1.36
     unin
    1.25
     floats
    1.25
     doubles
    1.25
     prints
    1.12
     docs
    1.07
     presentations
    1.06
     TED
    1.05
    Activations Density 0.029%

    No Known Activations