© 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. 8-RES-JB
    11. 2491
    Prev
    Next
    INDEX
    Explanations

    the word "some" followed by other descriptors or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional or varying levels of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CARD
    -0.67
    APTER
    -0.67
    iola
    -0.66
    urden
    -0.63
    rup
    -0.62
    rollers
    -0.61
    gon
    -0.61
    tis
    -0.61
    iano
    -0.60
    andon
    -0.59
    POSITIVE LOGITS
     unspecified
    0.97
    ones
    0.89
     inexplicable
    0.87
     undefined
    0.87
    how
    0.86
     embodiments
    0.86
     semblance
    0.84
     extent
    0.83
    place
    0.81
     unforeseen
    0.77
    Activations Density 0.050%

    No Known Activations