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. 17793
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resemble" and its variations, indicating comparisons or similarities

    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
    FT
    -0.86
    aer
    -0.74
    ttp
    -0.73
    arta
    -0.73
    Supp
    -0.70
    hal
    -0.69
    imb
    -0.68
    gard
    -0.68
    ³³³³
    -0.67
    duct
    -0.66
    POSITIVE LOGITS
    lihood
    1.55
     resembles
    1.17
     resembling
    1.08
     resemble
    0.99
     resembled
    0.96
     likeness
    0.94
    awei
    0.86
     resemblance
    0.82
     favorably
    0.80
     resemb
    0.79
    Activations Density 0.011%

    No Known Activations