© 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. 7-RES-JB
    11. 3732
    Prev
    Next
    INDEX
    Explanations

    verbs indicating potential or hypothetical actions that could have happened

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential consequences or implications of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lucky
    -0.68
    âĺ
    -0.66
     mash
    -0.65
     recall
    -0.65
     touring
    -0.64
     inspecting
    -0.64
    aq
    -0.63
     Lust
    -0.61
     unlucky
    -0.59
     shalt
    -0.59
    POSITIVE LOGITS
     been
    1.17
     arisen
    1.06
     Been
    1.03
    been
    0.97
     occurred
    0.97
     originated
    0.95
     resulted
    0.92
     caused
    0.89
     existed
    0.88
     sparked
    0.88
    Activations Density 0.141%

    No Known Activations