© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 6014
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to contextual information

    oai_token-act-pair · gpt-3.5-turbo

    references to context and its significance in various situations

    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
    ccoli
    -0.74
    STON
    -0.73
    deen
    -0.73
    ãĥīãĥ©
    -0.70
    loo
    -0.70
    uster
    -0.69
    oppable
    -0.69
    aah
    -0.67
    ongyang
    -0.66
    owship
    -0.66
    POSITIVE LOGITS
    ually
    1.01
    ual
    0.97
     context
    0.92
    uality
    0.84
     contexts
    0.81
     menus
    0.79
     Context
    0.76
    book
    0.74
    Impl
    0.71
     contextual
    0.71
    Activations Density 0.031%

    No Known Activations