© 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. 11-RES-JB
    11. 1152
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage or application of materials or products in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various materials and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    secut
    -0.61
    Reloaded
    -0.60
    orate
    -0.58
    rious
    -0.56
    icipated
    -0.56
    ļé
    -0.56
    ril
    -0.55
    itled
    -0.54
    rontal
    -0.54
     allele
    -0.54
    POSITIVE LOGITS
     alike
    0.96
     applications
    0.95
     purposes
    0.86
     nowadays
    0.86
     contexts
    0.84
     such
    0.82
     environments
    0.82
     ranging
    0.75
    .</
    0.74
     because
    0.73
    Activations Density 0.374%

    No Known Activations