INDEX

Explanations

terms related to sharpness or intensity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewImports

-0.80

WebControls

-0.77

ContentAsync

-0.72

 propOrder

-0.70

otoro

-0.68

photobucket

-0.67

Muri

-0.66

 options

-0.65

الحياه

-0.65

Fusion

-0.64

POSITIVE LOGITS

 sharp

1.85

 Sharp

1.78

sharp

1.68

 SHARP

1.66

Sharp

1.63

 sharpen

1.46

 sharper

1.46

 sharpness

1.43

 sharpening

1.36

 sharply

1.26

Activations Density 0.075%

terms related to sharpness or intensity

No Comments

No Known Activations