INDEX

Explanations

negations and phrases indicating absence or exceptions

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

 probably

-0.57

probably

-0.54

 skute

-0.53

 variously

-0.53

 purpoſe

-0.53

 ferdig

-0.53

 ſch

-0.53

 вполне

-0.50

 finalmente

-0.49

 Anſ

-0.49

POSITIVE LOGITS

OGND

0.72

 compromis

0.70

hésite

0.70

 compromise

0.70

 estekak

0.67

AndEndTag

0.66

 Taktlose

0.65

comprom

0.62

下载附件

0.62

MigrationBuilder

0.62

Activations Density 0.376%

negations and phrases indicating absence or exceptions

No Comments

No Known Activations