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. 8-RES-JB
    6. 15803
    Prev
    Next
    INDEX
    Explanations

    places and businesses in a city or town

    oai_token-act-pair · gpt-3.5-turbo

    statements about establishments that operate continuously

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anon
    -0.81
     neglig
    -0.76
     negligence
    -0.76
     abused
    -0.75
     abusive
    -0.75
     whiff
    -0.75
     syndrome
    -0.75
     fluct
    -0.74
     wob
    -0.74
     overest
    -0.74
    POSITIVE LOGITS
    Tickets
    1.01
    Construction
    0.88
    will
    0.87
    Beginning
    0.85
     Plans
    0.84
     Designed
    0.84
    Adds
    0.81
    Along
    0.80
    Located
    0.79
     Included
    0.78
    Activations Density 0.800%

    No Known Activations