INDEX

Explanations

repeated phrases or references in the text

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

DockStyle

-0.62

RegressionTest

-0.59

клопе

-0.56

wirtschaft

-0.52

ご了承ください

-0.52

Polecam

-0.49

 gawas

-0.49

 continuant

-0.48

下一篇

-0.47

chọn

-0.47

POSITIVE LOGITS

That

1.35

 That

1.34

THAT

1.24

 THAT

1.10

Thats

0.97

脚注の使い方

0.97

that

0.93

 Thats

0.90

thats

0.85

 BorderRadius

0.85

Activations Density 0.085%

repeated phrases or references in the text

No Comments

No Known Activations