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. 10-RES-JB
    6. 24177
    Prev
    Next
    INDEX
    Explanations

    conjunctions used to contrast or add information

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases and conjunctions that convey contrast or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.84
    ickets
    -0.81
     intervals
    -0.74
    itivity
    -0.73
    imation
    -0.73
    gency
    -0.72
    imize
    -0.72
    ision
    -0.72
    imum
    -0.71
    icals
    -0.70
    POSITIVE LOGITS
     obsessed
    1.30
     incapable
    1.30
     proud
    1.26
     inexperienced
    1.24
     prone
    1.23
     fluent
    1.23
     wiser
    1.21
     proficient
    1.20
     addicted
    1.20
     capable
    1.20
    Activations Density 0.331%

    No Known Activations