© 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. 19878
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of combining or merging

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "combine."

    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
     Passage
    -0.71
    writers
    -0.66
    keeper
    -0.66
     Myster
    -0.65
     Confederacy
    -0.65
    writer
    -0.65
     Payton
    -0.65
     friendly
    -0.63
    ħĭ
    -0.63
    ĪĴ
    -0.63
    POSITIVE LOGITS
    inations
    1.20
    inators
    1.05
    ination
    1.02
    ined
    1.02
    inatory
    1.01
    ocation
    0.99
    inated
    0.95
    ombs
    0.86
    inator
    0.85
    plet
    0.85
    Activations Density 0.010%

    No Known Activations