© 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 EvalsExportsinterp-engineNEWAPI 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. 5017
    Prev
    Next
    INDEX
    Explanations

    statements or phrases emphasizing the distinction between correlation and causation

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of conclusion or finality

    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
    ributes
    -0.85
     earthqu
    -0.81
     haul
    -0.78
     mosqu
    -0.77
    uers
    -0.77
     convoy
    -0.75
     awaited
    -0.74
     heir
    -0.70
     pledged
    -0.70
     corrid
    -0.70
    POSITIVE LOGITS
     Firstly
    1.30
     Specifically
    1.29
     Therefore
    1.28
     Hence
    1.24
     Whereas
    1.24
     Moreover
    1.23
     However
    1.22
     Thus
    1.22
     Typically
    1.21
     Nevertheless
    1.21
    Activations Density 0.662%

    No Known Activations