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. 19186
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to impressing or being impressed

    oai_token-act-pair · gpt-3.5-turbo

    words related to impressing or being impressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     saline
    -0.70
     starch
    -0.66
    nia
    -0.62
    angled
    -0.60
     refuge
    -0.60
     amino
    -0.59
    interrupted
    -0.59
    ossession
    -0.58
     captivity
    -0.58
    oops
    -0.58
    POSITIVE LOGITS
    mented
    1.08
    ively
    1.06
    ments
    0.98
    iated
    0.89
    ment
    0.88
    ences
    0.87
    MENTS
    0.85
    enced
    0.84
    MENT
    0.80
    eting
    0.80
    Activations Density 0.049%

    No Known Activations