© 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. 1-RES-JB
    11. 20387
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "what happens."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ondo
    -0.86
    otor
    -0.79
    airs
    -0.76
    zie
    -0.75
    ude
    -0.74
    ijk
    -0.74
    hetically
    -0.73
    urry
    -0.73
    ilts
    -0.72
    air
    -0.70
    POSITIVE LOGITS
     happen
    0.97
     happening
    0.83
    uate
    0.83
     Cthulhu
    0.80
     happened
    0.78
    Ñĭ
    0.77
    EStream
    0.75
    terday
    0.74
    rences
    0.74
     occurring
    0.73
    Activations Density 0.012%

    No Known Activations