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. 10-RES-JB
    6. 19251
    Prev
    Next
    INDEX
    Explanations

    mentions of watching or following events in a news context

    oai_token-act-pair · gpt-3.5-turbo

    the word "JUST" and its variations, indicating a focus on assertions or emphatic statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quo
    -0.67
     intimately
    -0.66
     proletariat
    -0.63
     faithfully
    -0.61
     thereof
    -0.60
     progressively
    -0.60
     fullest
    -0.59
     abundantly
    -0.58
    luster
    -0.58
     invari
    -0.57
    POSITIVE LOGITS
    ices
    1.22
     WATCHED
    1.19
    icia
    0.96
    ifications
    0.91
    ICE
    0.89
    iciary
    0.88
    itia
    0.86
    Giving
    0.86
    ICES
    0.86
    inian
    0.85
    Activations Density 0.028%

    No Known Activations