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. 8-RES-JB
    6. 19473
    Prev
    Next
    INDEX
    Explanations

    instances of criticism and pressure directed towards individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms associated with scrutiny, pressure, criticism, and backlash

    oai_token-act-pair · gpt-3.5-turbo
    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
    dimension
    -0.67
     cures
    -0.60
    osite
    -0.59
    ete
    -0.59
    tein
    -0.58
    aples
    -0.58
    swick
    -0.57
    onge
    -0.57
    Ign
    -0.57
    oos
    -0.56
    POSITIVE LOGITS
     stemming
    0.84
     owing
    0.78
    xual
    0.76
    ÄŁ
    0.70
     setbacks
    0.66
     alleging
    0.65
    back
    0.64
     regarding
    0.63
     levied
    0.63
     fallout
    0.63
    Activations Density 0.253%

    No Known Activations