INDEX

Explanations

language about storytelling and perspective, especially in the context of historical or cultural narratives.

oai_token-act-pair · gemini-2.0-flash

storytelling

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 story

-2.94

Story

-2.70

 Story

-2.67

story

-2.66

 STORY

-2.53

STORY

-2.31

 stories

-2.20

 Stories

-2.02

Stories

-1.99

stories

-1.95

POSITIVE LOGITS

LookAnd

0.48

InputBorder

0.47

})`

0.46

stateMutability

0.42

SequentialGroup

0.42

DockStyle

0.41

 AssemblyTitle

0.41

odha

0.40

')")

0.40

 tủ

0.40

Activations Density 1.451%

language about storytelling and perspective, especially in the context of historical or cultural narratives.

storytelling

No Comments

No Known Activations