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. 13675
    Prev
    Next
    INDEX
    Explanations

    keywords related to design elements and physical objects in a descriptive manner

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to design and aesthetics

    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
     Kaplan
    -0.58
    irement
    -0.56
     Aval
    -0.56
    LOS
    -0.54
    tz
    -0.53
    POS
    -0.50
    odcast
    -0.50
    lopp
    -0.49
     Emblem
    -0.49
    asma
    -0.48
    POSITIVE LOGITS
     alike
    1.62
     respectively
    1.28
     thereof
    1.14
     accordingly
    1.03
     thereafter
    0.93
     thereto
    0.91
     therein
    0.88
     versa
    0.84
    depending
    0.74
     afterward
    0.69
    Activations Density 3.166%

    No Known Activations