© 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. 2-RES-JB
    11. 12584
    Prev
    Next
    INDEX
    Explanations

    verbs related to cooking techniques

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cooking processes and strong emotional reactions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ULTS
    -0.71
    aimon
    -0.60
    hire
    -0.60
    ANY
    -0.60
    ---------
    -0.59
    EAR
    -0.59
     OWN
    -0.59
    cius
    -0.59
     deaf
    -0.58
     Moons
    -0.58
    POSITIVE LOGITS
    ing
    2.39
    ership
    1.40
    eering
    1.11
    edIn
    1.09
    ingham
    1.06
    ING
    1.04
    ingly
    1.00
    itives
    0.96
    ning
    0.95
    ington
    0.94
    Activations Density 0.087%

    No Known Activations