© 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. 7345
    Prev
    Next
    INDEX
    Explanations

    descriptions of equipment and tools used for specific purposes

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to construction and support structures

    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
     Zuckerberg
    -0.77
     dudes
    -0.77
    whatever
    -0.75
     shit
    -0.74
    fuck
    -0.74
     bullshit
    -0.73
    crime
    -0.73
     pissed
    -0.73
     feds
    -0.71
     shitty
    -0.71
    POSITIVE LOGITS
     recommends
    1.04
     preferably
    0.99
     recommended
    0.98
     Recommended
    0.95
     commonly
    0.94
    imum
    0.93
     advisable
    0.92
     recommend
    0.92
     optionally
    0.91
     preferred
    0.90
    Activations Density 0.818%

    No Known Activations