INDEX

Explanations

terms related to warranties and guarantees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

MessageOf

-0.57

 الحره

-0.50

 referrerpolicy

-0.48

 يتيمه

-0.47

EXTERN

-0.44

fuge

-0.43

zzleHttp

-0.43

发表于

-0.43

waite

-0.42

لينكات

-0.41

POSITIVE LOGITS

 warranty

0.87

 garansi

0.79

 Warranty

0.76

Warranty

0.74

 Garantie

0.70

 garantie

0.69

warranty

0.68

 warranties

0.67

 guarantee

0.64

 Guarantee

0.63

Activations Density 0.102%

terms related to warranties and guarantees

No Comments

No Known Activations