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. 6-RES-JB
    6. 2033
    Prev
    Next
    INDEX
    Explanations

    words related to the availability or prevalence of items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to availability and prevalence of options or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iverse
    -0.85
    asus
    -0.77
    erm
    -0.77
    robe
    -0.74
    inelli
    -0.71
    asm
    -0.69
    ney
    -0.69
    enegger
    -0.67
    hair
    -0.67
    imb
    -0.66
    POSITIVE LOGITS
     thereof
    0.84
     occurrence
    0.75
     Takeru
    0.67
     mismatch
    0.66
    lihood
    0.66
     OF
    0.65
     Rate
    0.64
    istence
    0.64
     rates
    0.64
     rate
    0.64
    Activations Density 0.057%

    No Known Activations