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. 10-RES-JB
    6. 9039
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or topic, possibly related to sports or events

    oai_token-act-pair · gpt-3.5-turbo
    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
    manship
    -0.78
     Brotherhood
    -0.68
    hower
    -0.61
     EntityItem
    -0.61
     Rouge
    -0.60
     Yankee
    -0.60
     occasion
    -0.59
     PowerPoint
    -0.58
     prompts
    -0.57
    lihood
    -0.57
    POSITIVE LOGITS
    oster
    1.43
    java
    1.17
    aming
    1.15
    jas
    1.13
    asted
    1.11
    asting
    1.05
    aches
    1.04
    vers
    1.04
    aching
    1.03
    zzi
    1.02
    Activations Density 0.018%

    No Known Activations