© 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. 4-RES-JB
    11. 13455
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of convergence, where multiple entities come together

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with convergence and merging

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

    No Comments

    Negative Logits
    ook
    -0.81
    iku
    -0.71
    asha
    -0.70
    asel
    -0.67
    avid
    -0.66
    aceutical
    -0.64
    akable
    -0.64
    estinal
    -0.64
    aiden
    -0.63
    avy
    -0.62
    POSITIVE LOGITS
     conver
    1.05
     converge
    0.81
    ãĥ¼ãĥĨãĤ£
    0.81
    inational
    0.78
    ivities
    0.70
    halla
    0.70
    ging
    0.70
    ilib
    0.69
     convergence
    0.68
    sonian
    0.68
    Activations Density 0.007%

    No Known Activations