© 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. 7010
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recommendations or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "should" indicating obligations or recommendations

    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
     Trails
    -0.72
    reality
    -0.71
     Puzzle
    -0.68
    ITED
    -0.68
    locked
    -0.65
    atile
    -0.63
    Soul
    -0.63
    ZI
    -0.63
    venture
    -0.61
    cule
    -0.60
    POSITIVE LOGITS
     be
    0.89
     preferably
    0.86
     ideally
    0.86
     surely
    0.79
     definitely
    0.78
    ['
    0.78
     probably
    0.77
    ered
    0.76
     therefore
    0.76
     theoretically
    0.75
    Activations Density 0.045%

    No Known Activations