© 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. 20869
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "the fact that"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the fact that."

    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
    aciously
    -0.66
    rup
    -0.66
    mes
    -0.63
    osing
    -0.62
    idelines
    -0.61
    ron
    -0.61
    boards
    -0.61
    gur
    -0.60
    OLOG
    -0.60
    thro
    -0.60
    POSITIVE LOGITS
     happened
    0.75
     hindsight
    0.74
     contradicts
    0.73
     they
    0.73
     accompanies
    0.72
     occurred
    0.69
     happens
    0.69
     THEY
    0.67
     occurs
    0.67
     transpired
    0.67
    Activations Density 0.130%

    No Known Activations