© 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. 8-RES-JB
    11. 19416
    Prev
    Next
    INDEX
    Explanations

    the character "ľ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to pointlessness or confusion

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     synerg
    -0.85
     territorial
    -0.78
     targeted
    -0.76
     indexed
    -0.75
     favor
    -0.74
     fragmented
    -0.73
     impacts
    -0.73
     consolidation
    -0.73
     migr
    -0.72
     dubbed
    -0.72
    POSITIVE LOGITS
    Yeah
    1.28
    Okay
    1.26
    Yes
    1.25
    What
    1.20
    Oh
    1.20
    Hey
    1.19
    Damn
    1.14
    Who
    1.13
    Sure
    1.13
    yeah
    1.12
    Activations Density 0.119%

    No Known Activations