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. 8-RES-JB
    6. 201
    Prev
    Next
    INDEX
    Explanations

    sentences describing processes or procedures

    oai_token-act-pair · gpt-3.5-turbo

    processes and elements related to ease and efficiency in tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to tasks or processes being easy or straightforward.

    oai_token-act-pair · gpt-4oTriggered by @tatsatx
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropolitan
    -0.81
     Ronald
    -0.78
    âĢİ
    -0.69
    Washington
    -0.68
    terday
    -0.66
     Reagan
    -0.65
    hillary
    -0.65
     Dwight
    -0.64
     Barack
    -0.64
    Donald
    -0.63
    POSITIVE LOGITS
     usability
    1.04
     beginner
    0.98
     usefulness
    0.96
     setups
    0.95
     beginners
    0.92
     playthrough
    0.91
     debugging
    0.91
     novice
    0.85
     encount
    0.84
     shenan
    0.81
    Activations Density 1.178%

    No Known Activations