INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Vidite

-0.98

 Paglinawan

-0.96

 AssemblyCulture

-0.89

RetentionPolicy

-0.84

 Baillargeon

-0.79

WireFormatLite

-0.76

sizeCache

-0.71

хьтан

-0.67

WithIOException

-0.65

tling

-0.62

POSITIVE LOGITS

 lượt

0.54

koľvek

0.51

 الدولى

0.50

خصة

0.49

 Weing

0.49

 لئے

0.46

 együtt

0.45

참고

0.45

sendTo

0.44

...”

0.44

Activations Density 0.793%

mathematical symbols and notations

No Comments

No Known Activations