© 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. 6-RES-JB
    11. 17141
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cases"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional situations or scenarios

    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
    ongyang
    -0.79
    opoly
    -0.70
    hesive
    -0.69
    kefeller
    -0.69
    gey
    -0.66
    scribe
    -0.65
    ancial
    -0.61
    oir
    -0.61
    uld
    -0.60
    redit
    -0.60
    POSITIVE LOGITS
     involving
    0.84
    hops
    0.77
    finder
    0.76
    hooting
    0.74
     cases
    0.71
    cases
    0.71
    rooms
    0.70
    places
    0.69
    hots
    0.68
    cale
    0.67
    Activations Density 0.027%

    No Known Activations