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. 20045
    Prev
    Next
    INDEX
    Explanations

    references to sports competitions involving the concept of "competition."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, particularly related to dictatorial or authoritative contexts

    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
    ned
    -1.01
    der
    -0.79
    selves
    -0.79
    meric
    -0.78
    iland
    -0.78
    waves
    -0.75
    ciation
    -0.75
    ming
    -0.73
    nery
    -0.71
    spect
    -0.69
    POSITIVE LOGITS
     XVI
    1.03
     Cumber
    0.99
    orian
    0.98
    orians
    0.93
    atorial
    0.91
    orius
    0.82
    ines
    0.79
    ine
    0.79
    ariat
    0.77
    atures
    0.74
    Activations Density 0.066%

    No Known Activations