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. 21674
    Prev
    Next
    INDEX
    Explanations

    phrases related to interconnectedness or relationships between entities

    oai_token-act-pair · gpt-3.5-turbo

    references to mutual support and connection between individuals

    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
    ships
    -0.68
    0002
    -0.68
    ees
    -0.65
    CHO
    -0.65
    ARS
    -0.63
    Naz
    -0.63
    Mos
    -0.61
    Hide
    -0.59
    \-
    -0.58
    Tour
    -0.58
    POSITIVE LOGITS
    worldly
    1.04
    dayName
    0.78
    emonic
    0.73
    ciating
    0.69
    inant
    0.68
    alian
    0.68
     baseman
    0.67
     panc
    0.67
     Flavoring
    0.64
    igham
    0.63
    Activations Density 0.023%

    No Known Activations