INDEX

Explanations

instances of numeric data or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 myſelf

-0.94

IntoConstraints

-0.85

 CURIAM

-0.83

 greateſt

-0.83

NameInMap

-0.81

Efq

-0.81

 مشين

-0.81

 ſtate

-0.81

contentLoaded

-0.80

tvguidetime

-0.80

POSITIVE LOGITS

0.71

0.57

<td>

0.56

0.53

ben

0.53

“

0.51

0.50

apikey

0.49

Str

0.49

あれば

0.47

Activations Density 0.314%

instances of numeric data or mathematical expressions

No Comments

No Known Activations