© 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. 9-RES-JB
    11. 20712
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "mit" at varying activation levels, potentially related to "mitigation", "Mittelstand" or other contexts where "mit" appears

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mit" and its derivatives, possibly related to medical or scientific concepts

    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
    ORD
    -0.77
    sword
    -0.76
    cloth
    -0.69
    ä¹ĭ
    -0.68
     snipp
    -0.67
    SHIP
    -0.67
     Borders
    -0.66
    ãĤ¦
    -0.65
    ĪĴ
    -0.65
     Frozen
    -0.64
    POSITIVE LOGITS
    igated
    1.42
    igation
    1.37
    igating
    1.35
    chell
    1.27
    ochond
    1.25
    igator
    1.20
    igators
    1.20
    iation
    1.17
    rog
    1.13
    chel
    1.06
    Activations Density 0.047%

    No Known Activations