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. 22246
    Prev
    Next
    INDEX
    Explanations

    dates of events

    oai_token-act-pair · gpt-3.5-turbo

    important dates and numerical events

    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
    cellence
    -0.84
    utics
    -0.76
     Scully
    -0.74
    players
    -0.69
    ateurs
    -0.68
     Contains
    -0.68
    utf
    -0.68
    lang
    -0.68
    ometers
    -0.66
    retty
    -0.66
    POSITIVE LOGITS
     edition
    0.99
     deadline
    0.97
     departure
    0.94
     arrival
    0.91
     episode
    0.89
     installment
    0.89
     version
    0.87
     announcement
    0.86
     presence
    0.84
     expiration
    0.83
    Activations Density 0.081%

    No Known Activations