© 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. 8-RES-JB
    11. 20025
    Prev
    Next
    INDEX
    Explanations

    sentences discussing facts or information

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain significant punctuation or structural markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contempl
    -0.86
     clut
    -0.85
     challeng
    -0.81
     heav
    -0.80
     emotion
    -0.80
     clutching
    -0.80
     pit
    -0.78
     indec
    -0.78
     clutch
    -0.78
     workspace
    -0.77
    POSITIVE LOGITS
     Indeed
    1.39
     Moreover
    1.34
     And
    1.31
     Presumably
    1.27
     Notably
    1.26
     Likewise
    1.25
     But
    1.25
     Therefore
    1.23
     Specifically
    1.22
     Interestingly
    1.22
    Activations Density 0.777%

    No Known Activations