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. 4721
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives that express certainty or comparison in comparison to something else

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating frequency or temporal aspects

    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
    •single token firings
    Fires strongly on " frequently", " often", " still", " continually", " usually", etc.

    No Comments

    Negative Logits
     Seym
    -0.81
     Azerb
    -0.62
    ollar
    -0.60
     Coke
    -0.57
     paramilitary
    -0.57
    perty
    -0.56
    bledon
    -0.55
    istani
    -0.54
     disobedience
    -0.54
     Princ
    -0.51
    POSITIVE LOGITS
     ];
    0.69
     refers
    0.69
     Released
    0.67
    iverse
    0.66
     ]
    0.65
     =>
    0.65
    20439
    0.65
     Asked
    0.64
    malink
    0.64
     Adds
    0.64
    Activations Density 0.147%

    No Known Activations