INDEX

Explanations

phrases related to data reporting or observation

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

containing "self" or similar forms

np_acts-logits-general · gemini-2.0-flash

words following punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tvguidetime

-0.90

wapV

-0.74

 Audiodateien

-0.68

protoimpl

-0.66

 الحره

-0.62

PRNewswire

-0.61

consulté

-0.60

 calendriers

-0.58

Xaml

-0.57

 المعيارى

-0.56

POSITIVE LOGITS

 myſelf

0.76

wiſe

0.72

ſelves

0.71

 houſe

0.70

 itſelf

0.67

ſelf

0.66

 doubtnut

0.65

SEGUIR

0.62

 pleaſure

0.61

ydable

0.59

Activations Density 0.159%

phrases related to data reporting or observation

containing "self" or similar forms

words following punctuation

No Comments

No Known Activations