INDEX

Explanations

words and phrases related to favorites and selections in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

migrationBuilder

-0.69

TypedDataSet

-0.64

interopRequire

-0.50

PathVariable

-0.49

crollView

-0.48

textTheme

-0.48

minecraft

-0.47

참고

-0.47

MEMORANDUM

-0.47

 &___

-0.46

POSITIVE LOGITS

 kaarangay

0.72

ness

0.70

 durumda

0.65

NESS

0.64

@"/

0.64

spesies

0.59

IntoConstraints

0.59

 status

0.57

再说

0.57

ByDefault

0.55

Activations Density 0.376%

words and phrases related to favorites and selections in various contexts

No Comments

No Known Activations