© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 7944
    Prev
    Next
    INDEX
    Explanations

    short phrases related to current events or news headlines

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation marks in discussions of serious topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     predec
    -0.78
    iste
    -0.71
     unprotected
    -0.69
     manif
    -0.68
     explan
    -0.67
     defe
    -0.66
     allocation
    -0.65
     mosqu
    -0.65
     shaving
    -0.63
     multiplication
    -0.62
    POSITIVE LOGITS
     Their
    0.90
     They
    0.89
     Besides
    0.85
     Its
    0.82
     *)
    0.82
     Such
    0.82
     These
    0.81
     Fortunately
    0.81
     Specifically
    0.81
     Additionally
    0.81
    Activations Density 0.487%

    No Known Activations