© 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. 11-RES-JB
    11. 14908
    Prev
    Next
    INDEX
    Explanations

    words related to pain relief or medical treatment

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitions in discourse

    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
    TW
    -0.69
    quet
    -0.67
    abit
    -0.65
    Correction
    -0.65
    Person
    -0.65
    someone
    -0.65
    Category
    -0.64
    iably
    -0.63
    a
    -0.63
    Either
    -0.63
    POSITIVE LOGITS
     cumbers
    0.82
     penchant
    0.81
     complexities
    0.78
     the
    0.77
     consequ
    0.77
     antics
    0.76
     sheer
    0.76
     intric
    0.75
     resultant
    0.74
     unbeliev
    0.74
    Activations Density 0.248%

    No Known Activations