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. 18325
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to personal responsibilities or moral duty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate emotional struggles or challenges faced by individuals

    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
    ropolitan
    -0.70
    hovah
    -0.70
    aughtered
    -0.67
    arij
    -0.66
    mbuds
    -0.64
    mop
    -0.63
    aucus
    -0.62
    anwhile
    -0.62
    artment
    -0.62
    vernment
    -0.62
    POSITIVE LOGITS
     adversity
    0.89
     stride
    0.74
     overcame
    0.73
     bravery
    0.70
     himself
    0.69
     teammates
    0.69
     teammate
    0.67
     unorthodox
    0.67
     composure
    0.67
     succeeds
    0.66
    Activations Density 1.023%

    No Known Activations