© 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. 7396
    Prev
    Next
    INDEX
    Explanations

    words related to academic achievement, achievements, and specific universities or colleges

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual content and related terminology

    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
     lawy
    -0.74
    ĩ
    -0.69
    ioned
    -0.67
    ACP
    -0.65
    chester
    -0.64
     sshd
    -0.64
    abouts
    -0.63
    âķIJâķIJ
    -0.62
     Defenders
    -0.61
    ideshow
    -0.60
    POSITIVE LOGITS
    ulative
    1.55
    ming
    1.23
    ulus
    1.08
    cum
    1.07
    ulates
    0.96
    ulate
    0.94
     Cum
    0.93
    mers
    0.91
    brance
    0.90
    mington
    0.87
    Activations Density 0.012%

    No Known Activations