© 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. 2-RES-JB
    11. 10409
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a specific range or period of time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "span" referring to duration or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tical
    -0.71
     GEAR
    -0.68
    tics
    -0.66
    icted
    -0.65
    ãĤº
    -0.64
    ãĥīãĥ©
    -0.63
    oaded
    -0.62
    Adds
    -0.62
    phis
    -0.61
     aspir
    -0.59
    POSITIVE LOGITS
    span
    1.33
     span
    1.19
    ning
    0.96
    ming
    0.90
     spans
    0.87
    olicy
    0.85
     Span
    0.85
     Chun
    0.84
    eworks
    0.82
    itime
    0.81
    Activations Density 0.004%

    No Known Activations