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. 7-RES-JB
    6. 8159
    Prev
    Next
    INDEX
    Explanations

    expressions related to affection or passion towards a specific topic or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing love or strong passion for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aunder
    -0.84
    eworks
    -0.82
    ratulations
    -0.76
    ureau
    -0.75
    ements
    -0.74
    alion
    -0.74
    pter
    -0.74
    ocument
    -0.73
     dispatched
    -0.71
    wcs
    -0.71
    POSITIVE LOGITS
     tink
    0.83
     sport
    0.80
     hobbies
    0.77
     sweets
    0.75
     hobby
    0.73
     motors
    0.72
     aesthetics
    0.72
     sports
    0.70
     adventure
    0.70
     poetry
    0.69
    Activations Density 0.186%

    No Known Activations