© 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. 10-RES-JB
    11. 13594
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions or expressing opinions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to censorship and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.59
    shown
    -0.59
    ENGTH
    -0.53
    Ĥª
    -0.52
    »Ĵ
    -0.48
    VERTISEMENT
    -0.48
     Hoo
    -0.47
    inguished
    -0.46
    INFO
    -0.46
    ãĤ«
    -0.46
    POSITIVE LOGITS
     because
    1.25
     whilst
    1.10
     lest
    1.05
     someday
    1.05
     whenever
    1.05
     unless
    1.00
     whereas
    0.99
     anymore
    0.98
     but
    0.95
     sooner
    0.92
    Activations Density 0.828%

    No Known Activations