INDEX

Explanations

sections of text that contain no relevant content or significant activation

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

HTML label tags

np_acts-logits-general · gemini-2.0-flash

labels and titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RegistryLite

-0.77

RUnlock

-0.72

ImageContext

-0.61

ThemeOverlay

-0.60

CppMethod

-0.58

setVerticalGroup

-0.55

APPLAUSE

-0.55

ISupport

-0.54

 DialogResult

-0.54

 protoimpl

-0.53

POSITIVE LOGITS

LabelTagHelper

1.03

 InputDecoration

0.63

 traditionnels

0.56

})}

0.55

ftagPool

0.55

 domanda

0.53

 labels

0.53

label

0.52

 perguntou

0.52

flich

0.50

Activations Density 0.040%

sections of text that contain no relevant content or significant activation

HTML label tags

labels and titles

No Comments

No Known Activations