INDEX

Explanations

phrases indicating opinions or suggestions about a situation, particularly in social or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ainfi

-1.01

 feroit

-0.88

 Monfieur

-0.86

 myſelf

-0.84

 scattata

-0.84

 nuages

-0.83

 pauv

-0.82

 zelve

-0.81

 pouvoit

-0.81

 abstrait

-0.81

POSITIVE LOGITS

had

0.98

had

0.77

has

0.77

Had

0.76

Has

0.74

 tiene

0.73

HAD

0.73

 punya

0.71

 have

0.71

 mempunyai

0.70

Activations Density 0.350%

phrases indicating opinions or suggestions about a situation, particularly in social or political contexts

No Comments

No Known Activations