INDEX

Explanations

words and phrases used to introduce an explanation or a reason.

oai_token-act-pair · gemini-2.0-flash

they

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

She

-1.60

She

-1.45

We

-1.34

We

-1.32

 Their

-1.19

Their

-1.15

He

-0.98

He

-0.94

 мы

-0.91

Мы

-0.91

POSITIVE LOGITS

 they

0.79

ImageContext

0.71

awtextra

0.71

 跳转至

0.65

 onCreateView

0.63

gridx

0.60

stdc

0.60

criminate

0.59

GenerationType

0.59

satunya

0.57

Activations Density 1.401%

words and phrases used to introduce an explanation or a reason.

they

No Comments

No Known Activations