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. 20044
    Prev
    Next
    INDEX
    Explanations

    objects or concepts related to geometry

    oai_token-act-pair · gpt-3.5-turbo

    geometrical shapes and their characteristics

    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
    Ĥİ
    -0.67
     Grimes
    -0.67
     reinvest
    -0.66
    icipated
    -0.66
     Tours
    -0.66
     Jennings
    -0.65
    2018
    -0.64
     Bezos
    -0.63
    review
    -0.63
     Headquarters
    -0.63
    POSITIVE LOGITS
     combinations
    1.04
     varieties
    1.01
     thereof
    0.97
     hybrids
    0.93
     unic
    0.88
     etc
    0.86
     equivalents
    0.84
     respectively
    0.83
     integers
    0.83
     depending
    0.83
    Activations Density 0.580%

    No Known Activations