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. 10-RES-JB
    6. 21045
    Prev
    Next
    INDEX
    Explanations

    phrases related to checking out publications or subscribing for more content

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to subscriptions or following content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    course
    -0.59
     Puzzles
    -0.59
     embr
    -0.58
    eers
    -0.58
     Nib
    -0.57
    soever
    -0.55
    cknowled
    -0.55
     acknowled
    -0.54
     assumes
    -0.54
     scram
    -0.53
    POSITIVE LOGITS
    çīĪ
    0.69
    bleacher
    0.66
    utenberg
    0.63
    BBC
    0.62
    Subscribe
    0.61
    aic
    0.59
    çİĭ
    0.57
    inventoryQuantity
    0.57
    sports
    0.57
    amacare
    0.56
    Activations Density 0.078%

    No Known Activations