INDEX

Explanations

mathematical symbols and variables commonly used in scientific notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

]:

-0.52

 others

-0.49

Diwedd

-0.49

 finally

-0.48

卷

-0.48

ipfel

-0.47

Kết

-0.47

WriteTagHelper

-0.47

 folgender

-0.46

testify

-0.46

POSITIVE LOGITS

CWE

0.69

FunctionFlags

0.66

isms

0.65

 RSSSF

0.61

 utafitiHapana

0.57

Nth

0.56

vernment

0.56

 кӀ

0.56

HttpPut

0.55

IndentedString

0.54

Activations Density 0.659%

mathematical symbols and variables commonly used in scientific notation

No Comments

No Known Activations