© 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. 4-RES-JB
    11. 2064
    Prev
    Next
    INDEX
    Explanations

    keywords related to future outcomes or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of outcomes or future possibilities

    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
    lua
    -0.75
    toe
    -0.68
    books
    -0.68
    mans
    -0.67
    PAC
    -0.67
    burg
    -0.67
    raph
    -0.66
    tick
    -0.65
    erie
    -0.65
    book
    -0.65
    POSITIVE LOGITS
    ities
    0.98
    ity
    0.98
    ITY
    0.92
    aneously
    0.88
     demise
    0.86
     downfall
    0.84
     embodiments
    0.81
    ITIES
    0.79
     winner
    0.76
     eventual
    0.75
    Activations Density 0.009%

    No Known Activations