© 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. 1-RES-JB
    11. 11216
    Prev
    Next
    INDEX
    Explanations

    words related to spatial alignment and positioning

    oai_token-act-pair · gpt-3.5-turbo

    references to "orientation," particularly in contexts related to physical, political, and sexual alignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.72
    女
    -0.68
    Ox
    -0.67
    ãģį
    -0.67
    soDeliveryDate
    -0.67
    ARD
    -0.66
    Interstitial
    -0.66
    Rare
    -0.65
    Exp
    -0.65
    Article
    -0.62
    POSITIVE LOGITS
     orientation
    1.37
    yip
    1.05
     orient
    1.01
    eering
    0.96
    xual
    0.90
    buquerque
    0.88
    jriwal
    0.80
     Orient
    0.78
     indoctr
    0.76
     ceremonies
    0.75
    Activations Density 0.005%

    No Known Activations