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. 11-RES-JB
    6. 4522
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "seems to" used in various contexts

    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
    called
    -0.68
    ashes
    -0.67
    noticed
    -0.62
    imore
    -0.61
    finding
    -0.61
    opens
    -0.61
    endale
    -0.60
    items
    -0.60
    types
    -0.60
    ãĤ¦ãĤ¹
    -0.59
    POSITIVE LOGITS
     imply
    1.13
     contradict
    1.09
     defy
    1.07
     indicate
    1.03
     condone
    1.03
     be
    0.99
     me
    0.99
     embody
    0.97
     confirm
    0.92
     correlate
    0.92
    Activations Density 0.054%

    No Known Activations