INDEX

Explanations

sentences that contain significant figures or data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

KommentareTeilen

-0.63

AddTagHelper

-0.62

دانشنامهٔ

-0.60

inguém

-0.59

########.

-0.58

下载附件

-0.58

 nemmeno

-0.56

 onCreateView

-0.55

Efq

-0.55

 unknownFields

-0.54

POSITIVE LOGITS

 among

2.17

 Among

2.01

Among

1.92

among

1.90

 amongst

1.80

 AMONG

1.69

 Amongst

1.68

 parmi

1.51

 blant

1.49

 antaranya

1.48

Activations Density 0.342%

sentences that contain significant figures or data

No Comments

No Known Activations