© 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. 9-RES-JB
    11. 20265
    Prev
    Next
    INDEX
    Explanations

    phrases ending with punctuation that indicate a strong statement or event

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks, indicating the conclusion of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wider
    -0.76
     caster
    -0.72
     compar
    -0.70
     prevalence
    -0.68
     pit
    -0.68
     shake
    -0.67
     unseen
    -0.67
     listener
    -0.66
     spectator
    -0.66
     intermediate
    -0.65
    POSITIVE LOGITS
     Instead
    1.34
     Specifically
    1.28
     During
    1.15
     Beginning
    1.14
     Firstly
    1.13
     Shortly
    1.11
     Called
    1.11
     Yesterday
    1.08
     Apparently
    1.06
     Using
    1.06
    Activations Density 0.492%

    No Known Activations