© 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. 3-RES-JB
    11. 4157
    Prev
    Next
    INDEX
    Explanations

    phrases related to catching up with someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "caught up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idia
    -0.83
     absence
    -0.66
    hof
    -0.65
    phia
    -0.65
     unification
    -0.64
     forwards
    -0.63
     expended
    -0.62
    imar
    -0.62
    oria
    -0.61
     shroud
    -0.61
    POSITIVE LOGITS
    CHAT
    0.74
     Sovere
    0.71
    Remote
    0.69
    ById
    0.68
    Jr
    0.68
     Turtles
    0.65
     Fresh
    0.63
    Footnote
    0.62
    tle
    0.61
    Cod
    0.59
    Activations Density 0.139%

    No Known Activations