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. 7-RES-JB
    6. 15093
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a thoughtful or insightful manner

    oai_token-act-pair · gpt-3.5-turbo

    instances of uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     multiplier
    -0.73
    venge
    -0.70
     acceleration
    -0.68
     Aurora
    -0.65
     acceler
    -0.64
     arteries
    -0.63
     Maxim
    -0.63
     virtuous
    -0.62
     raping
    -0.62
     synerg
    -0.59
    POSITIVE LOGITS
    Nevertheless
    1.18
    Nonetheless
    1.13
     Nonetheless
    1.09
     Nevertheless
    1.06
    Instead
    0.97
     nor
    0.93
     preferring
    0.91
     Instead
    0.91
    nor
    0.90
    Nor
    0.89
    Activations Density 1.010%

    No Known Activations