© 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. 7-RES-JB
    11. 20829
    Prev
    Next
    INDEX
    Explanations

    words related to dependencies or interdependencies between components or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dependence and interdependencies

    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
    ific
    -0.84
    ²¾
    -0.80
    efer
    -0.78
    mberg
    -0.76
    itz
    -0.76
    furt
    -0.76
    Ĥ¬
    -0.73
    izont
    -0.71
    \\\\\\\\
    -0.71
    wagen
    -0.71
    POSITIVE LOGITS
    encies
    1.11
    ency
    0.94
     dependency
    0.85
    doms
    0.77
     upon
    0.73
     strain
    0.70
     injection
    0.70
    ministic
    0.69
     cripp
    0.68
    cipline
    0.68
    Activations Density 0.051%

    No Known Activations