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. 3-RES-JB
    6. 14823
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    the term "maker" in various contexts, indicating the involvement of individuals or entities that create or produce something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.74
    rises
    -0.66
     Horses
    -0.66
     leash
    -0.63
     lap
    -0.63
    ctica
    -0.60
     Subjects
    -0.60
     Mariners
    -0.60
    ilan
    -0.59
    termination
    -0.58
    POSITIVE LOGITS
    maker
    0.90
    makers
    0.89
    furt
    0.87
    finder
    0.81
    pace
    0.79
    tenance
    0.79
    roid
    0.78
     extraord
    0.77
    pox
    0.76
    Sov
    0.73
    Activations Density 0.022%

    No Known Activations