© 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. 7-RES-JB
    11. 11237
    Prev
    Next
    INDEX
    Explanations

    phrases related to structural collapse

    oai_token-act-pair · gpt-3.5-turbo

    mentions of structural collapses, particularly related to significant events or buildings

    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
    lean
    -0.80
    prim
    -0.72
    travel
    -0.72
    qua
    -0.72
    vag
    -0.71
    yah
    -0.70
    cil
    -0.69
    ju
    -0.69
    Choice
    -0.68
    ledge
    -0.68
    POSITIVE LOGITS
    ulence
    0.91
     containment
    0.81
    ateral
    0.81
    opian
    0.80
     dism
    0.75
    hower
    0.74
     contag
    0.74
    ows
    0.73
     collapse
    0.73
    aughter
    0.72
    Activations Density 0.040%

    No Known Activations