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. 19827
    Prev
    Next
    INDEX
    Explanations

    adjectives related to decrease or decline

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or decline in health or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     scoop
    -0.81
    oops
    -0.78
    UNCH
    -0.73
    Method
    -0.69
    hots
    -0.67
    bang
    -0.66
    LGBT
    -0.65
    Jess
    -0.65
     HK
    -0.65
    isks
    -0.65
    POSITIVE LOGITS
     diminished
    2.36
     diminishing
    2.13
     waning
    2.03
     diminish
    2.00
     dimin
    1.82
     fatigue
    1.69
     fading
    1.66
     fade
    1.52
     faded
    1.48
     weakened
    1.47
    Activations Density 0.043%

    No Known Activations