© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    terms related to linking or connection

    oai_token-act-pair · gpt-3.5-turbo

    references to connective tissue and linking concepts

    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
    é¾į
    -0.68
     basil
    -0.65
    Merit
    -0.63
    ouk
    -0.61
    conn
    -0.60
     weighed
    -0.59
     @@
    -0.58
    oshenko
    -0.58
    teenth
    -0.57
    Ĥİ
    -0.56
    POSITIVE LOGITS
     dots
    0.90
    apters
    0.77
    MpServer
    0.77
     causation
    0.70
     referral
    0.70
    inki
    0.68
    ibly
    0.65
    ãĥ¼ãĥĨ
    0.62
     GPS
    0.62
    ortium
    0.62
    Activations Density 0.440%

    No Known Activations