© 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. 11-RES-JB
    11. 7497
    Prev
    Next
    INDEX
    Explanations

    descriptions of events involving tragedy or crime

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volunte
    -0.85
     consistency
    -0.84
     affili
    -0.78
     regenerate
    -0.78
     possible
    -0.77
     cellar
    -0.76
     reconc
    -0.75
     encount
    -0.75
     integ
    -0.74
     concess
    -0.73
    POSITIVE LOGITS
     Shortly
    1.49
     Immediately
    1.43
     Afterwards
    1.35
     Months
    1.33
     Within
    1.27
     Thirty
    1.27
     Following
    1.26
     Forty
    1.26
     Suddenly
    1.24
     Inspired
    1.23
    Activations Density 0.379%

    No Known Activations