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. 10-RES-JB
    6. 4244
    Prev
    Next
    INDEX
    Explanations

    sentences related to criticism or disapproval

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvantaged
    -0.55
     subcontract
    -0.54
     Reincarnated
    -0.54
    oppable
    -0.53
     ..............
    -0.52
     Tycoon
    -0.52
     discriminated
    -0.52
     customs
    -0.51
     Fighting
    -0.50
     Transition
    -0.50
    POSITIVE LOGITS
     reader
    0.84
     journalistic
    0.80
    ascript
    0.76
     rhetorical
    0.74
    reader
    0.74
    canon
    0.72
     cynicism
    0.72
    entious
    0.69
     editorial
    0.68
     readers
    0.68
    Activations Density 1.161%

    No Known Activations