© 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. 10-RES-JB
    11. 14047
    Prev
    Next
    INDEX
    Explanations

    sentences related to space missions and astronauts working in space

    oai_token-act-pair · gpt-3.5-turbo

    information related to space missions and spacecraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictionary
    -0.90
    Tea
    -0.81
     diction
    -0.79
     dag
    -0.79
    Muslims
    -0.78
    soType
    -0.78
    Ļ½
    -0.77
    ratom
    -0.77
     thug
    -0.77
     vigilante
    -0.77
    POSITIVE LOGITS
     SpaceX
    1.91
     NASA
    1.88
    NASA
    1.82
     spacecraft
    1.79
     astronauts
    1.74
     Orbital
    1.66
     astronaut
    1.58
     orbital
    1.52
     orbit
    1.52
     orbiting
    1.51
    Activations Density 0.362%

    No Known Activations