© 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. 3237
    Prev
    Next
    INDEX
    Explanations

    phrases indicating one example or part of several within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases emphasizing the notion of being just one among many, often in a context of comparison or exemplification

    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
    same
    -0.72
    iano
    -0.65
    regn
    -0.65
    nob
    -0.63
    raped
    -0.62
    owers
    -0.60
     disbanded
    -0.60
    then
    -0.60
    sleep
    -0.58
    acha
    -0.58
    POSITIVE LOGITS
     examples
    0.99
     scratching
    0.98
     iceberg
    0.94
     sampling
    0.90
     anecdotal
    0.87
     sympt
    0.86
     example
    0.81
     sample
    0.79
     symptom
    0.79
     illustration
    0.78
    Activations Density 0.115%

    No Known Activations