© 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. 1496
    Prev
    Next
    INDEX
    Explanations

    referenced to an organization or community called "Oasis" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to places or states of calm and refuge

    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
    etermined
    -0.66
    ned
    -0.65
    secut
    -0.65
     numbered
    -0.63
    rick
    -0.62
     Irving
    -0.62
    ammad
    -0.61
     hashes
    -0.61
    ounced
    -0.61
     Quadro
    -0.60
    POSITIVE LOGITS
    asis
    1.08
    olit
    0.88
    conservancy
    0.75
     Royale
    0.74
    osa
    0.71
     Sanctuary
    0.70
    hift
    0.69
    pora
    0.68
    orescence
    0.68
    acus
    0.68
    Activations Density 0.009%

    No Known Activations