INDEX

Explanations

uses of the verb "to be" and nouns about changes or questions

oai_token-act-pair · gemini-2.0-flash

followed

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 được

-0.70

 été

-0.66

was

-0.63

 essere

-0.61

 been

-0.59

 ถูก

-0.59

odic

-0.59

 être

-0.58

 werd

-0.57

been

-0.56

POSITIVE LOGITS

 followed

1.06

 Followed

0.87

 accompanied

0.83

followed

0.82

 preceded

0.75

 assisted

0.73

 complemented

0.73

 flanked

0.72

 acompan

0.69

Followed

0.69

Activations Density 3.149%

uses of the verb "to be" and nouns about changes or questions

followed

No Comments

No Known Activations