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. 1-RES-JB
    6. 3999
    Prev
    Next
    INDEX
    Explanations

    patterns around the phrase "at first glance"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to quick observations or initial impressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usual
    -0.76
    icted
    -0.75
    needs
    -0.75
    âĹ¼
    -0.72
    cel
    -0.71
    CENT
    -0.70
    norm
    -0.70
    é¾
    -0.67
    ricular
    -0.67
    raid
    -0.67
    POSITIVE LOGITS
     glance
    1.41
     glances
    1.06
    lessly
    0.85
     quizz
    0.81
     peek
    0.79
     gazing
    0.78
     glanced
    0.76
     blush
    0.75
     dag
    0.75
     inquire
    0.74
    Activations Density 0.005%

    No Known Activations