© 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. 2-RES-JB
    11. 9494
    Prev
    Next
    INDEX
    Explanations

    terms related to Albert Einstein and his theories, especially the theory of relativity

    oai_token-act-pair · gpt-3.5-turbo

    references to Albert Einstein and his theories

    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
    Ec
    -0.70
    izards
    -0.69
    iffs
    -0.68
    onies
    -0.67
    eless
    -0.65
     rout
    -0.65
    ieft
    -0.64
    icas
    -0.64
    groups
    -0.64
    Border
    -0.63
    POSITIVE LOGITS
     Einstein
    1.19
    instein
    0.87
     physicist
    0.85
     Radiation
    0.82
     relativity
    0.78
    enthal
    0.77
    elsen
    0.77
     Galile
    0.75
    sonian
    0.75
     physicists
    0.74
    Activations Density 0.011%

    No Known Activations