INDEX

Explanations

punctuation and formatting related to the presentation of information in text

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

Tokens after apostrophes

np_acts-logits-general · gemini-2.0-flash

covid

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HostException

-0.90

berdayakan

-0.79

AllAfrica

-0.77

indd

-0.76

//}

-0.70

 ویکی‌پدیای

-0.70

URLException

-0.69

apatalk

-0.69

يكب

-0.67

EndGlobalSection

-0.67

POSITIVE LOGITS

‍

0.82

0.60

 covid

0.57

 COVID

0.55

<strong>

0.51

 Moreover

0.49

 Covid

0.49

dė

0.48

‍

0.48

covid

0.48

Activations Density 0.055%

punctuation and formatting related to the presentation of information in text

Tokens after apostrophes

covid

No Comments

No Known Activations