© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9291
    Prev
    Next
    INDEX
    Explanations

    technical terms related to the field of physics

    oai_token-act-pair · gpt-3.5-turbo

    references to the discipline of physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥİ
    -0.78
    sg
    -0.75
    anza
    -0.75
    ieft
    -0.75
     Archdemon
    -0.74
    onymous
    -0.73
    ividual
    -0.72
    ibaba
    -0.70
    nants
    -0.70
    istle
    -0.69
    POSITIVE LOGITS
     physics
    1.22
     physicist
    1.17
     physicists
    1.16
     Physics
    1.01
     physic
    1.01
     sciences
    0.95
     maths
    0.88
    ysics
    0.85
    bending
    0.84
     astroph
    0.82
    Activations Density 0.016%

    No Known Activations