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. 15400
    Prev
    Next
    INDEX
    Explanations

    dates formatted in a specific style

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical information related to 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
     Cabrera
    -0.62
     Coun
    -0.62
     supervisor
    -0.61
     Tw
    -0.61
     Franco
    -0.59
     collectors
    -0.59
    ersen
    -0.58
     names
    -0.57
     purs
    -0.57
    stown
    -0.57
    POSITIVE LOGITS
    Posted
    0.96
    ³³³
    0.94
    Dear
    0.92
    BuyableInstoreAndOnline
    0.89
    Reviewer
    0.85
    ramid
    0.83
    ategories
    0.81
    Disclaimer
    0.80
    Guest
    0.79
    Subject
    0.79
    Activations Density 0.124%

    No Known Activations