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

    Neuronpedia

    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. 19767
    Prev
    Next
    INDEX
    Explanations

    references to desires or requests from individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to desires or preferences, particularly those expressed as "wishes."

    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
    cpp
    -0.66
    helle
    -0.65
    orously
    -0.65
    chin
    -0.64
    agonists
    -0.63
    anuts
    -0.63
     Kills
    -0.62
    ulative
    -0.62
    interstitial
    -0.62
    analy
    -0.62
    POSITIVE LOGITS
     wishes
    0.99
    bone
    0.95
     aloud
    0.94
    mares
    0.85
     wished
    0.85
    bones
    0.84
     wish
    0.79
     fulfil
    0.75
    bringer
    0.75
    Bone
    0.73
    Activations Density 0.010%

    No Known Activations