INDEX

Explanations

negation phrases and negative contractions related to actions

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

Rüyada

-1.04

GEBURTSDATUM

-1.03

 kaarangay

-0.93

 ErrIntOverflow

-0.86

 AssemblyVersion

-0.86

queryInterface

-0.83

SOUNDBITE

-0.82

 disambiguazione

-0.80

 pinulongan

-0.80

EDEFAULT

-0.78

POSITIVE LOGITS

’

1.01

0.94

↵↵

0.78

 wasn

0.75

mathrm

0.67

 Wasn

0.66

<eos>

0.65

isn

0.65

 shouldn

0.62

Wasn

0.60

Activations Density 2.389%

negation phrases and negative contractions related to actions

No Comments

No Known Activations