INDEX

Explanations

references to "things" and their various attributes or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Sapphire

-0.86

 δὲ

-0.83

 mères

-0.81

Переваги

-0.79

 RIPRODUZIONE

-0.78

structor

-0.78

ChildScrollView

-0.77

ferrer

-0.76

 hanem

-0.75

Dziękuję

-0.75

POSITIVE LOGITS

 things

2.25

Things

1.98

 Things

1.97

 THINGS

1.88

things

1.79

 thing

1.57

 Thing

1.55

THINGS

1.43

 Dinge

1.41

 cosas

1.41

Activations Density 0.051%

references to "things" and their various attributes or actions

No Comments

No Known Activations