© 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. 7-RES-JB
    11. 11179
    Prev
    Next
    INDEX
    Explanations

    the word "that" as part of a phrase indicating a strong belief or opinion

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.87
    ãĥīãĥ©
    -0.75
    IELD
    -0.73
    iped
    -0.71
    erve
    -0.69
    ciples
    -0.68
    aunder
    -0.68
    iky
    -0.67
    ipers
    -0.67
    cakes
    -0.66
    POSITIVE LOGITS
     contradicts
    0.84
     justifies
    0.74
     although
    0.73
     applies
    0.71
     qualifies
    0.71
     translates
    0.71
     sounded
    0.68
     sounds
    0.68
     happened
    0.68
     corresponds
    0.68
    Activations Density 0.244%

    No Known Activations