© 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. 0-RES-JB
    11. 14929
    Prev
    Next
    INDEX
    Explanations

    different ways or perspectives of doing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "differently" and variations of perspective or treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsis
    -0.61
    hold
    -0.59
    ounding
    -0.55
     Reign
    -0.55
     Lawrence
    -0.54
    ake
    -0.54
    watch
    -0.54
    ako
    -0.54
     finish
    -0.53
     Atlantic
    -0.52
    POSITIVE LOGITS
     differently
    3.92
    different
    1.78
     different
    1.58
     separately
    1.52
     Different
    1.51
     differ
    1.49
    Different
    1.44
     differed
    1.38
     differs
    1.38
     incorrectly
    1.26
    Activations Density 0.013%

    No Known Activations