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. 12652
    Prev
    Next
    INDEX
    Explanations

    the word "albeit" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating contrasts or exceptions

    oai_token-act-pair · gpt-3.5-turbo
    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
    orters
    -0.77
     Rhod
    -0.76
    rush
    -0.74
    enny
    -0.68
    aming
    -0.67
    rift
    -0.67
    hal
    -0.67
    ogy
    -0.67
    ugen
    -0.66
    ends
    -0.64
    POSITIVE LOGITS
    albeit
    0.98
     albeit
    0.91
     guiActiveUn
    0.82
    nown
    0.82
    soever
    0.81
     sparing
    0.78
    chery
    0.77
    beit
    0.73
    rolet
    0.73
    BIT
    0.72
    Activations Density 0.007%

    No Known Activations