INDEX

Explanations

phrases indicating specific cases or instances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 initComponents

-0.64

RenderAtEndOf

-0.45

parsedMessage

-0.41

featureID

-0.40

就去

-0.38

yscy

-0.38

IActionResult

-0.37

 pulse

-0.36

ItemBackground

-0.36

 briefly

-0.36

POSITIVE LOGITS

 cases

0.81

 casos

0.81

 case

0.76

 situations

0.75

 caso

0.75

 Fällen

0.71

ケース

0.70

 situaciones

0.65

 kasus

0.65

 situation

0.65

Activations Density 0.748%

phrases indicating specific cases or instances

No Comments

No Known Activations