INDEX

Explanations

phrases involving the word 'by' that indicate repetition over time

oai_token-act-pair · gemini-2.0-flash

Prepositions in descriptive contexts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Efq

-0.60

 Monfieur

-0.60

 незавершена

-0.59

 SUDOC

-0.57

 ―――――

-0.57

^(@)

-0.56

θος

-0.56

 itſelf

-0.55

InputLabel

-0.54

 -->>

-0.54

POSITIVE LOGITS

 للمعارف

0.56

 particulières

0.52

RenderAtEndOf

0.47

oolean

0.47

 automatiques

0.46

发表于

0.45

новниш

0.45

posedge

0.45

Abitanti

0.45

 kív

0.45

Activations Density 3.434%

phrases involving the word 'by' that indicate repetition over time

Prepositions in descriptive contexts

No Comments

No Known Activations