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. 17333
    Prev
    Next
    INDEX
    Explanations

    the phrase "just as"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "just as" indicating comparisons or similarities

    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
    TG
    -0.74
    Override
    -0.71
    Ve
    -0.70
     fixme
    -0.68
    eri
    -0.67
    roads
    -0.66
    ux
    -0.65
    RR
    -0.64
    bryce
    -0.64
    Mp
    -0.64
    POSITIVE LOGITS
     importantly
    1.06
    semble
    0.74
     advertised
    0.71
    pired
    0.67
    ratulations
    0.65
     stressed
    0.62
     soon
    0.61
     embold
    0.60
    emetery
    0.60
     tempted
    0.60
    Activations Density 0.021%

    No Known Activations