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. 1-RES-JB
    6. 17450
    Prev
    Next
    INDEX
    Explanations

    references to programming terms and concepts, particularly focusing on the term "Basic" and related programming terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Basic" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.75
    ._
    -0.74
    Jess
    -0.74
    ope
    -0.74
    _-
    -0.74
    oping
    -0.73
    essee
    -0.73
    MW
    -0.70
    ographers
    -0.69
    Sax
    -0.68
    POSITIVE LOGITS
     Basic
    1.02
    Basic
    0.83
    basic
    0.78
     Begin
    0.75
     Bulg
    0.72
    ritional
    0.71
     Leban
    0.70
    entle
    0.68
     Seym
    0.68
     Regions
    0.68
    Activations Density 0.009%

    No Known Activations