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. 0-RES-JB
    6. 21034
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a comparison or relationship between several items or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "amongst" and its variations, indicating a focus on social groups or collective contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ___
    -0.87
     canceled
    -0.81
     gray
    -0.69
    Newsletter
    -0.66
     cellphone
    -0.65
    Correction
    -0.64
     NAACP
    -0.62
     congressional
    -0.62
     ZIP
    -0.62
     probe
    -0.62
    POSITIVE LOGITS
     amongst
    3.21
     whilst
    1.82
     Whilst
    1.77
     among
    1.46
    among
    1.45
     amidst
    1.44
     util
    1.12
    Firstly
    1.09
     somew
    1.09
    ilst
    1.08
    Activations Density 0.010%

    No Known Activations