© 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. 4-RES-JB
    11. 10948
    Prev
    Next
    INDEX
    Explanations

    phrases related to space and astronomy

    oai_token-act-pair · gpt-3.5-turbo

    references to astronomical phenomena and objects

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

    No Comments

    Negative Logits
    iquette
    -0.86
     toile
    -0.84
     offend
    -0.82
     Criminal
    -0.80
     discretion
    -0.74
    ammy
    -0.74
    incerity
    -0.72
    ily
    -0.72
    itis
    -0.70
     Mens
    -0.70
    POSITIVE LOGITS
     orbiting
    1.24
     geological
    1.14
     astronomers
    1.12
     Kepler
    1.10
     orbits
    1.08
     spacecraft
    1.07
     orbital
    1.07
     radiation
    1.06
     scientists
    1.04
     infrared
    1.03
    Activations Density 0.868%

    No Known Activations