© 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. 10-RES-JB
    11. 6604
    Prev
    Next
    INDEX
    Explanations

    words related to a broad sense of comparison or evaluation of situations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "any" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endas
    -0.82
    redients
    -0.81
    wings
    -0.78
    redits
    -0.76
    ributes
    -0.74
    Rs
    -0.70
    appings
    -0.70
    scrib
    -0.69
    rez
    -0.69
    ickers
    -0.69
    POSITIVE LOGITS
    THING
    1.34
     conceivable
    1.29
     imaginable
    1.15
     given
    1.12
     sane
    1.07
    ONE
    0.97
     semblance
    0.95
     kind
    0.94
     sensible
    0.93
     decent
    0.92
    Activations Density 0.075%

    No Known Activations