© 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. 4-RES-JB
    11. 11375
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or a new development

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a change over time or new developments

    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
    ãĥ³ãĤ¸
    -0.69
    ãĥ´
    -0.66
    anon
    -0.64
     Provided
    -0.63
    WER
    -0.62
    Reviewer
    -0.61
     Native
    -0.61
    Quote
    -0.61
    FactoryReloaded
    -0.61
    aeda
    -0.60
    POSITIVE LOGITS
    anwhile
    0.78
    ences
    0.77
     confines
    0.73
    iatus
    0.72
     ende
    0.69
    ence
    0.68
     horizon
    0.67
     disappears
    0.67
    roups
    0.65
    abouts
    0.65
    Activations Density 0.093%

    No Known Activations