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. 0-RES-JB
    6. 15943
    Prev
    Next
    INDEX
    Explanations

    instances where the text is exclusively focused on a specific subject or group

    oai_token-act-pair · gpt-3.5-turbo

    the term "exclusively" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ripple
    -0.61
    reads
    -0.58
     citation
    -0.58
    remember
    -0.57
     note
    -0.55
     warnings
    -0.55
    aur
    -0.54
    Govern
    -0.54
    herty
    -0.54
     shook
    -0.54
    POSITIVE LOGITS
     exclusively
    3.63
     solely
    1.91
     exclusive
    1.70
     primarily
    1.58
    exclusive
    1.49
    clusively
    1.47
     extensively
    1.45
     predominantly
    1.43
     principally
    1.41
     entirely
    1.39
    Activations Density 0.008%

    No Known Activations