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. 9-RES-JB
    6. 11794
    Prev
    Next
    INDEX
    Explanations

    phrases related to severing relationships or ties with entities

    oai_token-act-pair · gpt-3.5-turbo

    references to severing or cancelling relationships, agreements, or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uzzle
    -0.69
    othermal
    -0.68
    ollah
    -0.61
    PLA
    -0.61
    ogeneous
    -0.60
    osite
    -0.60
    ãĤ©
    -0.59
    inal
    -0.58
    angled
    -0.58
    ixtures
    -0.57
    POSITIVE LOGITS
     altogether
    1.81
     entirely
    1.25
     indefinitely
    1.18
     abruptly
    1.13
     prematurely
    1.07
     due
    0.97
     outright
    0.95
     forever
    0.92
     fearing
    0.91
     voluntarily
    0.89
    Activations Density 0.492%

    No Known Activations