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. 1-RES-JB
    6. 19854
    Prev
    Next
    INDEX
    Explanations

    occurrences of words associated with glorification, endorsement, or validation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to glorification and testimonials, particularly in contexts involving certifications or accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tables
    -0.78
    manship
    -0.78
     setback
    -0.75
     Dynamics
    -0.74
    Iterator
    -0.73
     Procedure
    -0.73
     Warriors
    -0.73
     Spear
    -0.72
     Shade
    -0.71
    hner
    -0.71
    POSITIVE LOGITS
    ified
    1.38
    ifying
    1.18
    ifies
    1.10
     glor
    1.08
    ification
    1.05
    ifiable
    1.05
    itud
    1.01
    rets
    0.98
    ifications
    0.97
    uitous
    0.97
    Activations Density 0.012%

    No Known Activations