INDEX

Explanations

punctuation marks that indicate the start or end of lists or key points in a text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows colons or list markers

np_acts-logits-general · gemini-2.0-flash

enumerating items

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.99

-------------</

-0.95

 BitmapFactory

-0.83

mybatisplus

-0.79

 RequestMethod

-0.78

OGND

-0.77

resave

-0.76

AndEndTag

-0.76

 <>",

-0.76

enumi

-0.75

POSITIVE LOGITS

↵↵

1.34

↵

1.14

The

1.06

 namely

1.01

↵↵↵

0.97

0.93

↵↵↵↵

0.92

一是

0.90

<eos>

0.88

 Firstly

0.87

Activations Density 0.389%

punctuation marks that indicate the start or end of lists or key points in a text

Follows colons or list markers

enumerating items

No Comments

No Known Activations