INDEX

Explanations

personal pronouns in the first and third person

oai_token-act-pair · gemini-2.0-flash

Conversational text

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

 megfe

-0.59

jemah

-0.57

romole

-0.55

 való

-0.54

іга

-0.53

 löyty

-0.53

rometry

-0.53

ércio

-0.52

 kreatif

-0.52

yssey

-0.52

POSITIVE LOGITS

 Seen

0.72

 Given

0.70

 Taken

0.69

 Done

0.63

 taken

0.61

 Drawn

0.59

Given

0.58

 GIVEN

0.58

Seen

0.58

taken

0.58

Activations Density 11.834%

personal pronouns in the first and third person

Conversational text

No Comments

No Known Activations