© 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. 9-RES-JB
    11. 15571
    Prev
    Next
    INDEX
    Explanations

    scientific and anatomical terms related to the human body and physical phenomena

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to historical scientific theories and beliefs about the nature of Earth and the universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDA
    -0.77
     Warn
    -0.72
    andowski
    -0.66
    sers
    -0.64
     Enforcement
    -0.64
    aii
    -0.64
     Bans
    -0.62
    rouse
    -0.62
    ttp
    -0.62
     Appl
    -0.61
    POSITIVE LOGITS
     immutable
    1.15
     descended
    1.07
     biologically
    1.02
     intrinsically
    1.00
     inherently
    0.94
     evolving
    0.93
     evolved
    0.93
     fundamentally
    0.92
     interconnected
    0.91
     finite
    0.90
    Activations Density 0.474%

    No Known Activations