© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24395
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing or coordinating events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "arrange" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.89
    ku
    -0.88
    lean
    -0.83
    stone
    -0.73
    storms
    -0.71
    clamation
    -0.69
    tro
    -0.68
    fighter
    -0.68
    cart
    -0.67
    burgh
    -0.66
    POSITIVE LOGITS
     marriages
    1.00
     arrangements
    0.99
     arrang
    0.86
     arranged
    0.80
     Parenthood
    0.79
     seating
    0.76
     arranging
    0.76
     weddings
    0.74
     arrangement
    0.73
    MpServer
    0.69
    Activations Density 0.047%

    No Known Activations