INDEX

Explanations

terms related to warranties and guarantees

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

warranties

np_acts-logits-general · gemini-2.0-flash

lifetime and implied warranty

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.75

discipline

-0.54

KURZBESCHREIBUNG

-0.51

 discipline

-0.50

 Discipline

-0.50

 ExecuteAsync

-0.49

 disciplina

-0.49

awtextra

-0.49

 Betracht

-0.49

 Discipl

-0.47

POSITIVE LOGITS

 warranty

1.61

 Warranty

1.31

 warranties

1.30

warranty

1.22

 warran

1.16

Warranty

1.16

 guarantee

1.15

 WARRANTY

1.13

 garantie

1.04

 guarantees

0.99

Activations Density 0.174%

terms related to warranties and guarantees

warranties

lifetime and implied warranty

No Comments

No Known Activations