© 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. 10006
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    references to "some" and its varying contexts, implying a search for vague or nonspecific descriptors

    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
     Cycling
    -0.66
     yours
    -0.65
    uckle
    -0.62
     Clock
    -0.61
    ributes
    -0.61
    hips
    -0.59
    ades
    -0.58
    mers
    -0.58
    itten
    -0.57
    ourses
    -0.57
    POSITIVE LOGITS
    place
    1.40
    body
    1.38
    ones
    1.29
     sort
    1.28
     semblance
    1.21
     kind
    1.13
    ONE
    1.08
    how
    1.04
    THING
    0.92
     unspecified
    0.92
    Activations Density 0.103%

    No Known Activations