INDEX

Explanations

words like "means" and "indicate," which imply something.

oai_token-act-pair · gemini-2.0-flash

Explanations using the word "means"

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

 ―――――

-0.85

новниш

-0.83

IVEREF

-0.75

extAlignment

-0.71

tagHelperRunner

-0.71

ArrowToggle

-0.71

seamnă

-0.71

ViewFeatures

-0.71

PerformLayout

-0.71

 становника

-0.69

POSITIVE LOGITS

 that

0.89

 they

0.80

we

0.76

he

0.64

0.59

that

0.57

it

0.56

she

0.55

 there

0.52

you

0.51

Activations Density 2.020%

words like "means" and "indicate," which imply something.

Explanations using the word "means"

No Comments

No Known Activations