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. 4-RES-JB
    6. 5790
    Prev
    Next
    INDEX
    Explanations

    terms related to formal processes or interactions, such as agreements, petitions, reviews, notices, warnings, mechanisms, incidents, exemptions, and roles

    oai_token-act-pair · gpt-3.5-turbo

    words related to formal documentation and regulatory processes

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

    No Comments

    Negative Logits
    Flight
    -0.59
    Entry
    -0.56
    Bee
    -0.56
    Delivery
    -0.56
    scape
    -0.54
    Ł
    -0.54
     Cabin
    -0.53
     Insect
    -0.53
    Buzz
    -0.52
    Die
    -0.51
    POSITIVE LOGITS
    poons
    1.10
    pring
    1.00
    uggest
    0.92
    mith
    0.90
    hips
    0.87
    ometimes
    0.85
    ourcing
    0.84
     ranging
    0.82
    hift
    0.82
    heet
    0.82
    Activations Density 0.607%

    No Known Activations