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. 11-RES-JB
    6. 3361
    Prev
    Next
    INDEX
    Explanations

    the contraction "do not" in various forms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "don't" or variations of negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -1.02
     princ
    -0.99
     challeng
    -0.86
     satell
    -0.81
     accomp
    -0.81
     nomine
    -0.81
     newcom
    -0.77
     conduc
    -0.76
    anwhile
    -0.76
     tremend
    -0.75
    POSITIVE LOGITS
    âĢ
    1.84
    't
    1.39
    ´
    1.34
    Ê
    1.28
    Ä
    1.28
    âĪ
    1.27
    ÃŃ
    1.24
    ãĢ
    1.22
    ¨
    1.22
    ̶
    1.20
    Activations Density 0.064%

    No Known Activations