© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1852
    Prev
    Next
    INDEX
    Explanations

    mentions of things diverging or deviating from a common path

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "diverge" and its variations

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

    No Comments

    Negative Logits
    ORN
    -0.77
    HAEL
    -0.73
    CHA
    -0.71
    EEK
    -0.71
     Introduced
    -0.67
    ORED
    -0.67
    AAAA
    -0.66
    ellen
    -0.65
    Fax
    -0.61
    ORE
    -0.61
    POSITIVE LOGITS
    gencies
    1.21
    gent
    1.12
    ging
    0.98
    ministic
    0.98
    wcs
    0.93
     diver
    0.91
    gence
    0.88
    tic
    0.87
    vernment
    0.86
    minist
    0.86
    Activations Density 0.010%

    No Known Activations