© 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. 6-RES-JB
    11. 17860
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression or development in time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "by the time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avored
    -0.78
    avorite
    -0.68
    urb
    -0.68
    sson
    -0.67
    eanor
    -0.66
    awan
    -0.66
    ettel
    -0.65
    MET
    -0.64
    redited
    -0.62
    seek
    -0.62
    POSITIVE LOGITS
    liest
    0.73
    birth
    0.73
    bell
    0.64
     Polly
    0.64
     Thatcher
    0.63
    lines
    0.61
    builder
    0.61
     Conserv
    0.61
     adulthood
    0.61
    Reloaded
    0.61
    Activations Density 0.011%

    No Known Activations