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. 21552
    Prev
    Next
    INDEX
    Explanations

    the phrase "has nothing to do with" followed by a non-zero activation of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of connection or relevance between subjects

    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
    soDeliveryDate
    -0.86
    VERTISEMENT
    -0.73
     coats
    -0.66
     Advertisement
    -0.64
    quickShipAvailable
    -0.63
    TION
    -0.63
    ahime
    -0.60
     Dane
    -0.60
    pointers
    -0.60
    riger
    -0.59
    POSITIVE LOGITS
     satisfy
    1.07
    adies
    0.94
     celebrate
    0.93
     learn
    0.91
     ensure
    0.90
     acquire
    0.88
     appease
    0.87
    ggles
    0.87
     protect
    0.87
    asted
    0.85
    Activations Density 0.281%

    No Known Activations