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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1847
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'That.'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase 'That' used at the beginning of sentences or 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
    osponsors
    -1.01
    phthal
    -0.91
    paces
    -0.85
    emis
    -0.83
    hops
    -0.81
    icons
    -0.80
    pots
    -0.79
    Downloadha
    -0.79
    busters
    -0.78
    ports
    -0.76
    POSITIVE LOGITS
     fateful
    1.39
     afternoon
    1.16
     evening
    1.14
     prompted
    1.12
     resulted
    1.09
     night
    1.09
     culminated
    1.07
     morning
    1.06
     same
    1.06
     coincided
    1.03
    Activations Density 0.148%

    No Known Activations