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. 3-RES-JB
    6. 14660
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is restricted to a specific group or circumstance

    oai_token-act-pair · gpt-3.5-turbo

    the term "exclusively" and its related usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    former
    -0.76
    SCP
    -0.75
    olesterol
    -0.71
    dfx
    -0.71
    ulz
    -0.67
    Afee
    -0.67
    papers
    -0.66
    enegger
    -0.66
     Ske
    -0.66
     Straw
    -0.65
    POSITIVE LOGITS
     exclusively
    1.10
     geared
    0.78
     tailored
    0.77
     owned
    0.74
     bred
    0.73
     tuned
    0.72
    aturdays
    0.71
     conform
    0.71
     marketed
    0.70
     unrestricted
    0.70
    Activations Density 0.012%

    No Known Activations