Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23885
    Prev
    Next
    INDEX
    Explanations

    phrases related to disc golf

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hugs
    -0.80
     Blasio
    -0.71
     Hunts
    -0.69
    BILITIES
    -0.68
     Unemployment
    -0.68
     salaries
    -0.66
    FX
    -0.66
    rones
    -0.66
    onyms
    -0.66
     Barker
    -0.65
    POSITIVE LOGITS
     disc
    3.90
     discs
    2.70
     Disc
    2.51
    Disc
    1.85
    disc
    1.81
     disk
    1.50
     disks
    1.35
     Disk
    1.19
    Disk
    1.14
    disk
    1.05
    Activations Density 0.034%

    No Known Activations