© 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. 9-RES-JB
    11. 7479
    Prev
    Next
    INDEX
    Explanations

    words related to the X-Men comic series

    oai_token-act-pair · gpt-3.5-turbo

    references to "X-Men" in various contexts and expressions related to the franchise

    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
     EntityItem
    -0.78
    ufact
    -0.76
     digestion
    -0.68
     aback
    -0.65
     cannibal
    -0.64
     âĶľ
    -0.62
    Ùİ
    -0.62
     breakdown
    -0.61
     introducing
    -0.60
     adopting
    -0.60
    POSITIVE LOGITS
    rays
    1.08
    Factor
    1.03
    Ray
    1.02
    shaped
    1.02
    Men
    0.99
    factor
    0.99
    cellent
    0.98
    ray
    0.97
    axis
    0.97
    Wing
    0.92
    Activations Density 0.027%

    No Known Activations