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. 10-RES-JB
    6. 20043
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "you" or "I" is followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the first time" or references to past experiences

    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
     meantime
    -0.70
    now
    -0.64
     retaining
    -0.61
    utical
    -0.58
     provisional
    -0.58
    urity
    -0.58
     nowhere
    -0.58
     Prepar
    -0.57
    redients
    -0.57
     Dhabi
    -0.57
    POSITIVE LOGITS
     ever
    1.08
     EVER
    1.05
     interacted
    1.04
     ventured
    1.00
     encountered
    1.00
     bothered
    0.99
     touched
    0.98
     interfered
    0.97
     encount
    0.97
     visited
    0.97
    Activations Density 0.155%

    No Known Activations