© 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. 23820
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements or conditions for achieving specific outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional actions or intentions

    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
    Written
    -0.80
    TL
    -0.72
    blogspot
    -0.69
    LESS
    -0.66
     Printed
    -0.66
    option
    -0.64
    DragonMagazine
    -0.64
    ////////////////////////////////
    -0.63
     [&
    -0.61
     drifted
    -0.60
    POSITIVE LOGITS
     qualify
    1.08
     survive
    0.90
     justify
    0.89
     convince
    0.81
     overcome
    0.80
     Survive
    0.79
     ensure
    0.77
     satisfy
    0.77
     gain
    0.75
     guarantee
    0.75
    Activations Density 0.270%

    No Known Activations