INDEX

Explanations

instances of conflict or tension between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ujednoznacz

-0.73

حياته

-0.68

 références

-0.67

 itſelf

-0.67

下载附件

-0.67

 postIndex

-0.65

OOTDTY

-0.65

Cordialement

-0.64

 autorité

-0.64

حياتها

-0.62

POSITIVE LOGITS

tagext

0.46

 timp

0.46

 дописавши

0.45

何を

0.44

 night

0.42

 tadi

0.42

 hired

0.42

she

0.41

 time

0.41

↵↵

0.40

Activations Density 0.101%

instances of conflict or tension between characters

No Comments

No Known Activations