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. 4-RES-JB
    6. 3562
    Prev
    Next
    INDEX
    Explanations

    relative comparisons or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a comparative or relative relationship between different entities or concepts

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

    No Comments

    Negative Logits
    spr
    -1.02
    ERG
    -0.94
    storm
    -0.86
    eret
    -0.82
    inis
    -0.79
    iere
    -0.77
    ̶
    -0.75
    dk
    -0.74
    hner
    -0.74
    Ö¼
    -0.74
    POSITIVE LOGITS
     humidity
    1.07
     ease
    0.85
     pronoun
    0.84
     newcomer
    0.83
     pronouns
    0.81
     importance
    0.80
     autonomy
    0.79
     abund
    0.79
     newcom
    0.78
     pressures
    0.78
    Activations Density 0.009%

    No Known Activations