INDEX

Explanations

the word "the" when it appears near locations like "nation" or "United States"

oai_token-act-pair · gemini-2.0-flash

pronouns and common nouns

np_token-act-pair-logits · gpt-4o-mini

say "United"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 gynhyrchwyd

-0.79

DoubleQuotes

-0.75

 ་་

-0.73

 ―――――

-0.65

 raiſ

-0.63

 Daß

-0.63

 ſte

-0.62

 ſmall

-0.61

 houſe

-0.61

 Theſe

-0.61

POSITIVE LOGITS

MemoryWarning

0.73

ulados

0.54

her

0.53

 Trump

0.51

his

0.50

saw

0.50

 malha

0.49

zum

0.49

 Thousand

0.49

rungsseite

0.48

Activations Density 1.919%

the word "the" when it appears near locations like "nation" or "United States"

pronouns and common nouns

say "United"

No Comments

No Known Activations