© 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. 546
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sirhan" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    the name "Han" or variations of it

    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
    ISION
    -0.62
     remotely
    -0.60
     binary
    -0.60
     Eucl
    -0.59
     stakes
    -0.59
     smarter
    -0.59
     Skydragon
    -0.59
     Clicker
    -0.58
     Replay
    -0.57
    below
    -0.57
    POSITIVE LOGITS
    igans
    1.21
    abal
    1.01
    igan
    0.99
    ov
    0.93
    ovsky
    0.92
    agan
    0.89
    ogens
    0.86
    ogen
    0.86
    adan
    0.86
    thal
    0.85
    Activations Density 0.012%

    No Known Activations