© 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. 1-RES-JB
    11. 23090
    Prev
    Next
    INDEX
    Explanations

    phrases related to departments and coordination

    oai_token-act-pair · gpt-3.5-turbo

    references to "LL" likely indicating a specific movie or television series, possibly titles or episodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lished
    -0.79
    ãĥĩ
    -0.73
    rament
    -0.73
    repe
    -0.67
     Situation
    -0.66
    ItemTracker
    -0.64
    board
    -0.64
    hold
    -0.63
    detail
    -0.63
    EStream
    -0.63
    POSITIVE LOGITS
    LL
    1.39
    inois
    1.04
    oyd
    1.02
    IGH
    0.99
    UTION
    0.94
    uminati
    0.93
    ING
    0.92
    iard
    0.91
    IX
    0.89
    ION
    0.89
    Activations Density 0.012%

    No Known Activations