© 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. 6359
    Prev
    Next
    INDEX
    Explanations

    technical phrases related to work or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate predictions or expectations about future outcomes

    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
    pires
    -0.59
     Sina
    -0.57
     allegedly
    -0.56
    inus
    -0.55
    CHA
    -0.54
    sych
    -0.54
    afia
    -0.54
    oons
    -0.53
    pired
    -0.50
    Privacy
    -0.49
    POSITIVE LOGITS
     someday
    1.06
     anytime
    0.93
     sooner
    0.85
     sometime
    0.82
    omever
    0.77
     whatever
    0.76
     tomorrow
    0.75
     whichever
    0.74
     accordingly
    0.74
     ASAP
    0.73
    Activations Density 1.071%

    No Known Activations