© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 912
    Prev
    Next
    INDEX
    Explanations

    references to particles in the context of physics

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific particles

    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
    HCR
    -0.92
    orsi
    -0.91
    doms
    -0.82
    atility
    -0.81
    ongs
    -0.79
    kinson
    -0.77
    azeera
    -0.77
    ashington
    -0.76
    dk
    -0.75
    é»Ĵ
    -0.75
    POSITIVE LOGITS
     physicist
    1.22
     particle
    1.21
     physicists
    1.09
     accelerator
    0.92
     Physics
    0.87
     Collider
    0.87
     physics
    0.84
     beam
    0.79
    ERN
    0.78
    plane
    0.76
    Activations Density 0.009%

    No Known Activations