INDEX

Explanations

references to governmental or organizational entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 فريبيس

-0.54

atchewan

-0.51

cxx

-0.51

ഏ

-0.51

<>());

-0.50

 Litu

-0.49

 Beal

-0.48

migrationBuilder

-0.47

onAttach

-0.46

bleau

-0.46

POSITIVE LOGITS

 وتسجيلات

0.92

 officers

0.73

 islands

0.71

 agency

0.68

 agencies

0.67

webElement

0.67

Према

0.61

原始内容存档于

0.61

 arşivlendi

0.60

UnknownFields

0.60

Activations Density 0.129%

references to governmental or organizational entities

No Comments

No Known Activations