Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19386
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in 'ally'

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate actions or states related to collective or mutual experiences

    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
     soap
    -0.57
     nothing
    -0.56
     dw
    -0.55
     Tes
    -0.54
     Weber
    -0.53
     Unicode
    -0.52
     Fu
    -0.52
     Tah
    -0.52
     gl
    -0.52
     Eck
    -0.51
    POSITIVE LOGITS
    ally
    4.77
    ALLY
    2.63
    ality
    2.28
    arily
    1.75
    als
    1.75
    ively
    1.68
    istically
    1.64
    alities
    1.64
    ially
    1.59
    ually
    1.55
    Activations Density 0.009%

    No Known Activations