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. 22545
    Prev
    Next
    INDEX
    Explanations

    specific named entities starting with "The"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "The"

    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
     beforehand
    -0.73
    /"
    -0.72
     himself
    -0.70
     thereby
    -0.69
     theirs
    -0.68
     partake
    -0.67
     with
    -0.67
     themselves
    -0.67
     directly
    -0.67
     thereof
    -0.67
    POSITIVE LOGITS
    resa
    1.51
    oret
    1.38
    odore
    1.28
    ories
    1.12
    atre
    1.07
     Latest
    1.04
    orem
    1.03
     Basics
    0.98
     easiest
    0.97
     simplest
    0.96
    Activations Density 0.223%

    No Known Activations