© 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. 8-RES-JB
    11. 1279
    Prev
    Next
    INDEX
    Explanations

    full stops (periods) at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of sentences

    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
    iets
    -0.67
     conductor
    -0.61
    ude
    -0.60
     monop
    -0.58
     masc
    -0.58
     tyr
    -0.57
     transporter
    -0.57
     matte
    -0.56
     colour
    -0.56
    ikuman
    -0.55
    POSITIVE LOGITS
     Needless
    1.03
     Such
    1.01
     Specifically
    0.98
    SPONSORED
    0.96
     Moreover
    0.95
     Indeed
    0.94
    ↵
    0.92
     Essentially
    0.92
     Furthermore
    0.92
     Additionally
    0.91
    Activations Density 0.762%

    No Known Activations