© 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 EvalsExportsinterp-engineNEWAPI 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. 11039
    Prev
    Next
    INDEX
    Explanations

    terms related to economic activities and projects

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "generate" in different contexts

    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
    ĺħ
    -0.68
    ded
    -0.66
    hai
    -0.63
     Unified
    -0.62
    yer
    -0.61
    fax
    -0.59
    ENA
    -0.58
     Landing
    -0.57
     Disclosure
    -0.57
     reality
    -0.57
    POSITIVE LOGITS
    ational
    1.13
    icity
    1.10
    ator
    1.09
    ators
    1.08
    ative
    0.98
    andom
    0.96
    ations
    0.95
    osity
    0.95
    gener
    0.93
    ãĥ«
    0.88
    Activations Density 0.007%

    No Known Activations