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. 7736
    Prev
    Next
    INDEX
    Explanations

    contractions where the word "not" is involved

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions related to denial or negation

    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
     lucky
    -0.83
     glad
    -0.79
     thankful
    -0.77
     guessing
    -0.74
     watches
    -0.71
     praying
    -0.70
     preparing
    -0.69
     inspecting
    -0.69
     Seeking
    -0.68
     blogging
    -0.68
    POSITIVE LOGITS
     occur
    1.13
     outweigh
    1.11
     ripple
    1.07
     resonate
    1.04
     occurred
    1.03
     dissip
    1.02
     encompass
    0.99
     detract
    0.98
     coincide
    0.98
     reverber
    0.97
    Activations Density 0.384%

    No Known Activations