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. 9-RES-JB
    6. 12591
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical objects or phenomena, including measurements and locations

    oai_token-act-pair · gpt-3.5-turbo

    specific references to objects and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Consent
    -0.77
     deferred
    -0.74
    prem
    -0.73
     Editors
    -0.72
     Promotion
    -0.72
    },"
    -0.71
     editorial
    -0.70
    ettings
    -0.69
     Policies
    -0.69
     reservation
    -0.69
    POSITIVE LOGITS
     sightings
    1.34
     sighting
    1.33
     hovering
    1.15
     spotted
    1.07
     UFOs
    1.07
     photographed
    1.06
     resembling
    1.04
     resembled
    1.04
     orbiting
    1.03
     lurking
    1.01
    Activations Density 0.544%

    No Known Activations