Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24218
    Prev
    Next
    INDEX
    Explanations

    phrases related to projects or programs

    oai_token-act-pair · gpt-3.5-turbo

    sentences containing the verb "is" along with phrases indicating status or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburg
    -0.67
    hedon
    -0.66
    bury
    -0.64
    unks
    -0.62
    teness
    -0.61
    fire
    -0.61
     Martial
    -0.59
     resorts
    -0.57
    âĨ
    -0.55
    oso
    -0.54
    POSITIVE LOGITS
     slated
    1.21
     expected
    1.18
     intended
    1.07
     scheduled
    1.06
     aimed
    1.01
     envisioned
    1.00
     currently
    0.99
     meant
    0.99
     designed
    0.98
     comprised
    0.98
    Activations Density 0.241%

    No Known Activations