INDEX

Explanations

filler words and pronouns at the starts of phrases along with words related to business partnerships

oai_token-act-pair · gemini-2.0-flash

our

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 your

-0.50

Our

-0.50

our

-0.49

bootstrapcdn

-0.48

Our

-0.47

our

-0.47

 nosso

-0.46

seu

-0.40

 trova

-0.40

 admiten

-0.39

POSITIVE LOGITS

脚注の使い方

0.90

__":

0.77

 مشارکت‌کنندگان

0.73

 myſelf

0.73

atoon

0.73

 themſelves

0.73

CppMethod

0.72

)";

0.71

enumi

0.70

eradish

0.69

Activations Density 1.367%

filler words and pronouns at the starts of phrases along with words related to business partnerships

our

No Comments

No Known Activations