© 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. 3-RES-JB
    11. 23748
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of convergence

    oai_token-act-pair · gpt-3.5-turbo

    references to convergence or converging processes

    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
    ook
    -0.88
    asha
    -0.75
    aiden
    -0.74
    iku
    -0.72
    »Ĵ
    -0.68
    asel
    -0.67
    ooks
    -0.67
    aceutical
    -0.67
    acht
    -0.66
    avid
    -0.65
    POSITIVE LOGITS
     conver
    1.14
    ãĥ¼ãĥĨãĤ£
    0.93
     converge
    0.81
    ging
    0.80
    gent
    0.77
    ãĤ¤
    0.72
    rite
    0.70
    ibles
    0.69
    mentation
    0.69
    iances
    0.68
    Activations Density 0.006%

    No Known Activations