INDEX

Explanations

phrases or references related to legal or regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

RectangleBorder

-0.90

出版年

-0.88

 CreateTagHelper

-0.87

 MainAxisSize

-0.85

principalColumn

-0.80

ChildScrollView

-0.77

الحياه

-0.75

writeFieldEnd

-0.73

istoitu

-0.72

?».

-0.72

POSITIVE LOGITS

0.55

ish

0.52

<eos>

0.51

↵

0.48

0.47

держи

0.47

anti

0.46

就

0.46

ma

0.45

leştir

0.45

Activations Density 0.204%

phrases or references related to legal or regulatory contexts

No Comments

No Known Activations