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. 4-RES-JB
    6. 21563
    Prev
    Next
    INDEX
    Explanations

    mannerisms or behaviors described in a particular manner

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "manner" in various contexts

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

    No Comments

    Negative Logits
    Dust
    -0.78
    rament
    -0.69
     Lyn
    -0.69
     Patri
    -0.68
    ovie
    -0.67
    hemat
    -0.65
     Hansen
    -0.62
    tek
    -0.62
    ILL
    -0.62
    minster
    -0.61
    POSITIVE LOGITS
    isms
    1.18
     manner
    0.83
    othy
    0.75
     dictated
    0.74
     largeDownload
    0.73
    able
    0.73
     fashion
    0.73
    ably
    0.72
    uation
    0.72
    abus
    0.71
    Activations Density 0.012%

    No Known Activations