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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 10826
    Prev
    Next
    INDEX
    Explanations

    negations or denials

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey 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
    éĹĺ
    -0.89
    è¿
    -0.73
    oided
    -0.70
    çļ
    -0.69
    WAY
    -0.68
    éĥ
    -0.68
    åº
    -0.67
    çĶŁ
    -0.67
    æĥ
    -0.66
    itcher
    -0.65
    POSITIVE LOGITS
     necessarily
    1.07
    icable
    0.99
    orious
    0.96
    hin
    0.96
     uncommon
    0.95
     exactly
    0.92
     advisable
    0.87
     quite
    0.87
     easy
    0.87
    epad
    0.86
    Activations Density 0.086%

    No Known Activations