© 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. 9-RES-JB
    11. 20823
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases starting with "There is" followed by certain content related to different topics

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there is" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ares
    -0.77
    bies
    -0.74
    ooters
    -0.72
     retrie
    -0.66
     cylinders
    -0.62
    gets
    -0.60
    teenth
    -0.59
    olds
    -0.59
    chairs
    -0.59
    stocks
    -0.59
    POSITIVE LOGITS
     ample
    1.11
     plenty
    1.00
     no
    0.99
     disagreement
    0.97
     precedent
    0.94
     overlap
    0.94
    evidence
    0.89
     evidence
    0.89
     nothing
    0.88
     considerable
    0.87
    Activations Density 0.138%

    No Known Activations