© 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. 3-RES-JB
    11. 1570
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a shift in focus or attention

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in the meantime" or similar expressions indicating transition or time management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ized
    -0.81
    asted
    -0.73
    pled
    -0.73
    bold
    -0.70
    lic
    -0.68
    defined
    -0.67
    ammy
    -0.67
    oplan
    -0.65
    coded
    -0.65
    driving
    -0.65
    POSITIVE LOGITS
    ï¸
    0.80
    adays
    0.77
    uality
    0.76
    noon
    0.75
    Ñı
    0.73
     awaiting
    0.70
    hern
    0.67
     nep
    0.66
     meantime
    0.66
    ðĿ
    0.66
    Activations Density 0.006%

    No Known Activations