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. 18936
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a personal statement or opinion

    oai_token-act-pair · gpt-3.5-turbo

    statements that express honesty and personal admissions

    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
     retreating
    -0.70
     dissolve
    -0.69
    ·
    -0.64
    ibility
    -0.64
     unden
    -0.58
     ransom
    -0.58
    hya
    -0.58
     enshr
    -0.57
     sqor
    -0.57
     backdrop
    -0.57
    POSITIVE LOGITS
     impressed
    0.79
    é¾įåĸļ士
    0.73
    \'
    0.73
     ROCK
    0.72
     disappointed
    0.71
     MUCH
    0.69
     NEVER
    0.69
     THANK
    0.68
     amazed
    0.68
     surprised
    0.65
    Activations Density 0.370%

    No Known Activations