INDEX

Explanations

the word "single" preceded by "every"

oai_token-act-pair · gemini-2.0-flash

single

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

cokinetics

-0.44

之

-0.43

colta

-0.43

licus

-0.43

eep

-0.43

entrion

-0.43

AIN

-0.43

dequeue

-0.43

 Baik

-0.43

⇆

-0.42

POSITIVE LOGITS

 every

1.60

every

1.55

Every

1.50

 Every

1.50

EVERY

1.38

 EVERY

1.31

Chaque

1.30

 each

1.25

 Each

1.20

 Chaque

1.20

Activations Density 0.764%

the word "single" preceded by "every"

single

No Comments

No Known Activations