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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16683
    Prev
    Next
    INDEX
    Explanations

    references to the company SpaceX

    oai_token-act-pair · gpt-3.5-turbo

    mentions of SpaceX and its associated projects or vehicles, particularly the Falcon rockets

    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
    ãĥĥãĥĪ
    -0.80
    cum
    -0.76
    bred
    -0.71
    à¨
    -0.70
    epad
    -0.68
    venge
    -0.68
     Geral
    -0.67
    pron
    -0.66
    iscons
    -0.65
     Dane
    -0.65
    POSITIVE LOGITS
     SpaceX
    0.94
     rockets
    0.89
     Falcon
    0.83
     rocket
    0.81
     capsules
    0.79
     spacecraft
    0.78
    heed
    0.78
     spaceship
    0.75
     satellites
    0.74
    rocket
    0.74
    Activations Density 0.008%

    No Known Activations