INDEX

Explanations

instances of the term "switch" and variations related to programming or control flow statements

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

The token "switch"

np_acts-logits-general · gemini-2.0-flash

switch and switchgrass

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

thâu

-0.72

✨:

-0.57

 européennes

-0.54

AndEndTag

-0.54

lot

-0.53

athione

-0.52

ViewFeatures

-0.50

seamnă

-0.50

IntoConstraints

-0.50

tagext

-0.49

POSITIVE LOGITS

 switches

1.06

 Switch

0.98

 switch

0.98

 Switches

0.97

Switch

0.91

SWITCH

0.91

 switched

0.90

 SWITCH

0.89

 swit

0.84

 switching

0.83

Activations Density 0.063%

instances of the term "switch" and variations related to programming or control flow statements

The token "switch"

switch and switchgrass

No Comments

No Known Activations