© 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. 10-RES-JB
    11. 7845
    Prev
    Next
    INDEX
    Explanations

    phrases related to knowledge or expertise

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate knowledge or awareness

    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
    ermanent
    -0.73
    cohol
    -0.72
    clusive
    -0.71
    ãĤ´ãĥ³
    -0.70
     sidx
    -0.70
    ciation
    -0.69
    thren
    -0.69
    ItemTracker
    -0.69
    reau
    -0.68
    venants
    -0.68
    POSITIVE LOGITS
     how
    1.23
     firsthand
    1.15
     instinctively
    1.06
     better
    1.06
     exactly
    1.03
     what
    0.94
    ledged
    0.93
     best
    0.92
     intimately
    0.91
     nothing
    0.90
    Activations Density 0.101%

    No Known Activations