INDEX

Explanations

terms related to warranties and their coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.70

 discipline

-0.50

uxxxx

-0.49

 disciplina

-0.49

 Discipline

-0.49

 Règlement

-0.48

discipline

-0.48

 صوتيه

-0.48

igneur

-0.46

 Discipl

-0.46

POSITIVE LOGITS

 warranty

1.53

 Warranty

1.26

warranty

1.20

 warranties

1.19

Warranty

1.12

 warran

1.08

 WARRANTY

1.08

 guarantee

1.07

 garantie

0.97

 warranted

0.94

Activations Density 0.232%

terms related to warranties and their coverage

No Comments

No Known Activations