© 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. 2-RES-JB
    11. 18667
    Prev
    Next
    INDEX
    Explanations

    references to published research papers in academic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to published research papers and academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strongh
    -0.78
     lockout
    -0.74
    vil
    -0.73
     Isles
    -0.73
    vict
    -0.72
    dos
    -0.71
     eviction
    -0.70
     celebr
    -0.67
    venge
    -0.67
     vot
    -0.67
    POSITIVE LOGITS
     biomedical
    1.13
     biologist
    1.06
     Researchers
    1.04
     researcher
    1.04
     researchers
    1.03
    ournals
    1.01
     scientist
    0.99
     neuroscience
    0.99
     Scientist
    0.99
     biologists
    0.98
    Activations Density 0.581%

    No Known Activations