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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2999
    Prev
    Next
    INDEX
    Explanations

    negations or denials in statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ
    -0.79
    éĹĺ
    -0.73
    interstitial
    -0.71
    çīĪ
    -0.68
     Turns
    -0.67
    è¿
    -0.64
    WAY
    -0.63
    å¥
    -0.63
     Tours
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    POSITIVE LOGITS
     necessarily
    1.44
    icably
    1.27
    icable
    1.16
    withstanding
    1.03
     yet
    1.01
     exactly
    1.01
    necess
    0.95
    epad
    0.91
    orious
    0.91
    eworthy
    0.91
    Activations Density 0.205%

    No Known Activations