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. 0-RES-JB
    6. 2954
    Prev
    Next
    INDEX
    Explanations

    terms related to conversion or transformation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "conversion" and its plural form in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gale
    -0.70
    liam
    -0.69
    strong
    -0.68
    ofi
    -0.67
    ushi
    -0.65
    rants
    -0.65
     nervously
    -0.64
    Scene
    -0.64
    Squ
    -0.64
     Nurse
    -0.63
    POSITIVE LOGITS
     conversion
    4.07
     conversions
    3.73
     Conversion
    3.31
     converting
    2.40
     convert
    2.16
     converter
    2.10
     converted
    2.09
     converts
    1.91
     Convert
    1.68
     Convers
    1.61
    Activations Density 0.013%

    No Known Activations