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. 9-RES-JB
    6. 15237
    Prev
    Next
    INDEX
    Explanations

    adjectives describing negative or challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey a sense of difficulty, discomfort, or negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.71
    iffe
    -0.70
    ;;
    -0.69
    abwe
    -0.69
    OIL
    -0.67
    biased
    -0.67
    hey
    -0.66
    BW
    -0.65
    utics
    -0.64
    outube
    -0.64
    POSITIVE LOGITS
    est
    1.55
    liest
    1.20
    ness
    1.17
     confines
    1.14
     aftermath
    1.07
     possibility
    1.01
     notion
    0.97
     assumption
    0.95
     nature
    0.95
     culmination
    0.93
    Activations Density 0.310%

    No Known Activations