© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15327
    Prev
    Next
    INDEX
    Explanations

    texts related to the Paleocene and Eocene epochs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geological epochs and time periods

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

    No Comments

    Negative Logits
    cipled
    -0.82
    xtap
    -0.82
    channelAvailability
    -0.80
    isSpecialOrderable
    -0.79
    ierrez
    -0.78
    cohol
    -0.76
    liga
    -0.76
    è»
    -0.75
    rette
    -0.74
    ãĥ´ãĤ¡
    -0.72
    POSITIVE LOGITS
     civilizations
    1.00
     Era
    0.94
     Homo
    0.93
     Archae
    0.90
     fossils
    0.90
     ancestors
    0.88
     Egyptians
    0.88
     civilisation
    0.87
    ocene
    0.86
     ancestor
    0.85
    Activations Density 0.134%

    No Known Activations