INDEX

Explanations

negations or qualifiers that diminish or oppose statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

PPP

-0.64

 Kuba

-0.63

 esmeralda

-0.63

 Frieden

-0.62

PPP

-0.61

 Belk

-0.60

Aro

-0.60

 dorada

-0.59

ellees

-0.59

 Puma

-0.59

POSITIVE LOGITS

Not

1.04

Not

1.01

 estimés

0.92

NOT

0.90

NOT

0.88

Personendaten

0.87

not

0.85

copg

0.84

not

0.83

تقاوى

0.79

Activations Density 0.099%

negations or qualifiers that diminish or oppose statements

No Comments

No Known Activations