© 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. 10-RES-JB
    6. 5267
    Prev
    Next
    INDEX
    Explanations

    detailed instructions or technical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    statements about exceptions and their impact within systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.76
    Republic
    -0.70
     Britons
    -0.63
     grips
    -0.62
    razil
    -0.62
    Fran
    -0.61
     Europe
    -0.60
     Hispan
    -0.60
    olitan
    -0.60
     Countries
    -0.59
    POSITIVE LOGITS
     incidental
    1.25
     merely
    1.14
     meaningless
    1.13
     superflu
    1.10
     irrelevant
    1.07
     distracting
    1.06
     detract
    1.06
     omission
    1.03
     unintentional
    1.03
     unnecessary
    1.02
    Activations Density 0.508%

    No Known Activations