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. 0-RES-JB
    6. 14583
    Prev
    Next
    INDEX
    Explanations

    adjectives intensifying a condition or statement

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or descriptors emphasizing the degree of something

    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
     LP
    -0.61
     peer
    -0.60
     territory
    -0.59
     assignments
    -0.58
     board
    -0.58
     staging
    -0.58
     o
    -0.58
     rein
    -0.57
     recl
    -0.57
     set
    -0.56
    POSITIVE LOGITS
    very
    4.03
    extremely
    2.04
    quite
    1.73
    Very
    1.63
    highly
    1.53
     VERY
    1.47
    pretty
    1.38
    really
    1.36
    completely
    1.32
    absolutely
    1.31
    Activations Density 0.017%

    No Known Activations