© 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. 3-RES-JB
    11. 453
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making a bold statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking a stand or making declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.90
    catentry
    -0.87
    processing
    -0.71
    vous
    -0.68
    hell
    -0.66
    acho
    -0.64
     redistributed
    -0.64
    Balt
    -0.63
     <-
    -0.63
    jing
    -0.61
    POSITIVE LOGITS
    TextColor
    0.65
    issan
    0.64
     bounds
    0.64
     paddle
    0.64
     desks
    0.63
     STAND
    0.63
    akable
    0.63
     principled
    0.63
     pedest
    0.61
    enance
    0.61
    Activations Density 0.108%

    No Known Activations