© 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. 1-RES-JB
    11. 3853
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing completeness or entirety

    oai_token-act-pair · gpt-3.5-turbo

    the concept of 'wholeness' or completeness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Blade
    -0.75
    cl
    -0.62
    Lt
    -0.56
    ministic
    -0.56
    Adv
    -0.55
     Cutter
    -0.55
    CL
    -0.55
    bid
    -0.54
     Racer
    -0.54
    Sensor
    -0.53
    POSITIVE LOGITS
    heartedly
    1.32
    hearted
    0.89
     gam
    0.69
     thing
    0.68
    ciating
    0.67
     whole
    0.67
     darn
    0.63
     breadth
    0.62
    ãĤ¨ãĥ«
    0.61
    oter
    0.60
    Activations Density 0.013%

    No Known Activations