© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18497
    Prev
    Next
    INDEX
    Explanations

    words related to positive momentum or energy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "k."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •words starting with k

    No Comments

    Negative Logits
    terday
    -0.72
    LECT
    -0.71
     unlaw
    -0.70
    ãĥ¯
    -0.68
     Creed
    -0.68
    éĹĺ
    -0.68
    hedon
    -0.67
    ÙĴ
    -0.67
    IBLE
    -0.67
    byter
    -0.66
    POSITIVE LOGITS
    itty
    1.07
    rieg
    1.06
    idd
    1.06
    won
    1.02
    ratom
    1.01
    appa
    0.98
    etchup
    0.98
    uk
    0.95
    ansas
    0.95
    ipp
    0.94
    Activations Density 0.014%

    No Known Activations