© 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. 10-RES-JB
    11. 13877
    Prev
    Next
    INDEX
    Explanations

    phrases describing groups of people

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itor
    -0.72
     Begins
    -0.72
    lear
    -0.69
    noon
    -0.68
     Compared
    -0.65
    uthor
    -0.64
     Firstly
    -0.64
    ieth
    -0.63
    umar
    -0.63
    agos
    -0.62
    POSITIVE LOGITS
    etc
    1.13
     even
    0.97
     assorted
    0.97
     other
    0.92
    whatever
    0.90
     ultimately
    0.88
     otherwise
    0.86
     downright
    0.84
     etc
    0.82
     finally
    0.81
    Activations Density 0.189%

    No Known Activations