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. 17630
    Prev
    Next
    INDEX
    Explanations

    the word "There" at the beginning of a statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "There" indicating the existence or presence of something

    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
     pound
    -0.72
     micro
    -0.71
     digest
    -0.69
     grav
    -0.68
     ed
    -0.68
     CJ
    -0.67
     scar
    -0.67
     favour
    -0.67
     rad
    -0.65
     break
    -0.64
    POSITIVE LOGITS
    abouts
    1.07
     fortun
    0.97
    ngth
    0.97
    ometimes
    0.95
    hovah
    0.95
    olkien
    0.92
    ilst
    0.92
    ntil
    0.91
    ortmund
    0.87
    GoldMagikarp
    0.86
    Activations Density 0.050%

    No Known Activations