© 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. 611
    Prev
    Next
    INDEX
    Explanations

    structural elements within a text, such as introductory phrases and transitions

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "similarly" or phrases that compare similar ideas

    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
    Engineers
    -0.68
    ãĥ¥
    -0.66
    Deal
    -0.65
    interstitial
    -0.59
    Cause
    -0.58
    assed
    -0.57
    Associated
    -0.57
     enthus
    -0.57
    Accessory
    -0.56
    offs
    -0.56
    POSITIVE LOGITS
     however
    1.24
     though
    0.92
     although
    0.86
     meanwhile
    0.85
     please
    0.84
     according
    0.79
     moreover
    0.78
     albeit
    0.71
     alas
    0.70
    dds
    0.69
    Activations Density 0.468%

    No Known Activations