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. 1014
    Prev
    Next
    INDEX
    Explanations

    negations, particularly the word "not."

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of denial

    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
     Tours
    -0.74
    ãĤ¼
    -0.71
    kamp
    -0.70
    éĥ
    -0.66
    å¥
    -0.65
    çļ
    -0.65
    udeau
    -0.63
    ously
    -0.62
    USH
    -0.62
     Inventory
    -0.62
    POSITIVE LOGITS
     necessarily
    1.22
    icably
    1.20
    epad
    1.19
    hin
    1.16
    icable
    1.12
     gonna
    1.06
     exactly
    1.03
     bothered
    0.99
     entirely
    0.94
     bothering
    0.93
    Activations Density 0.103%

    No Known Activations