Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 10734
    Prev
    Next
    INDEX
    Explanations

    phrases related to a sports team being among the best

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusion or being part of a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.89
    ulum
    -0.73
    ourse
    -0.69
     excitement
    -0.68
     answer
    -0.68
    swer
    -0.67
     heartbeat
    -0.67
    itably
    -0.67
     suspense
    -0.65
    thening
    -0.65
    POSITIVE LOGITS
    Ĭ±
    0.78
     Rowling
    0.73
    ilver
    0.72
    reader
    0.68
    ItemTracker
    0.68
    76561
    0.68
     Roz
    0.67
    mere
    0.66
     Gors
    0.65
    aterasu
    0.65
    Activations Density 0.000%

    No Known Activations