© 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. 24072
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "subcontracted" or "substituted"

    oai_token-act-pair · gpt-3.5-turbo

    words related to "sub" and its various forms and contexts

    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
    steen
    -0.75
    bourg
    -0.71
     roses
    -0.66
    shapeshifter
    -0.66
    urga
    -0.61
    usalem
    -0.60
    ouk
    -0.59
     interchange
    -0.58
     Nim
    -0.57
    bery
    -0.57
    POSITIVE LOGITS
    ł
    0.92
    incial
    0.85
    ¿
    0.82
    Saharan
    0.82
    ittees
    0.82
    ranean
    0.80
    ctive
    0.79
    reshold
    0.77
    ²
    0.76
    isans
    0.76
    Activations Density 0.068%

    No Known Activations