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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2204
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative descriptions of things, especially those containing the word "badly"

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing negative conditions or experiences

    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
    uality
    -0.80
    cript
    -0.79
    iferation
    -0.71
    ership
    -0.70
    htaking
    -0.70
    itivity
    -0.70
     paternity
    -0.68
    itures
    -0.68
    criptions
    -0.68
     Parenthood
    -0.68
    POSITIVE LOGITS
     behaved
    1.01
     beaten
    0.91
     suited
    0.88
     effected
    0.83
     mistaken
    0.82
     poisoned
    0.80
     tarn
    0.80
     damaged
    0.80
     harmed
    0.78
     deteriorated
    0.78
    Activations Density 0.035%

    No Known Activations