INDEX

Explanations

words related to changing one thing for another

oai_token-act-pair · gemini-2.0-flash

switch

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 switch

-2.25

 switching

-2.13

 Switch

-2.09

 switches

-2.05

Switch

-2.02

 switched

-2.02

 Switching

-1.98

 SWITCH

-1.90

Switching

-1.88

switching

-1.84

POSITIVE LOGITS

tagHelperRunner

0.62

OrNull

0.49

 verbe

0.48

almaz

0.47

 unob

0.47

披

0.45

IContainer

0.45

част

0.45

日至

0.44

 Gump

0.43

Activations Density 14.727%

words related to changing one thing for another

switch

No Comments

No Known Activations