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. 24390
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports transactions and events

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships or associations

    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
    ippi
    -0.65
     resolutions
    -0.64
    ories
    -0.61
     Creat
    -0.61
    yg
    -0.60
     endif
    -0.60
     fuelled
    -0.59
    devices
    -0.59
     conver
    -0.56
     meanings
    -0.56
    POSITIVE LOGITS
     whom
    0.92
    assad
    0.78
    bilt
    0.70
     waivers
    0.69
    tesy
    0.68
    adem
    0.67
     pseudonym
    0.66
     VK
    0.65
    frey
    0.64
    ov
    0.64
    Activations Density 0.300%

    No Known Activations