INDEX

Explanations

negative responses or rejections

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

 виправивши

-0.84

{}\

-0.82

"{\

-0.79

 समीक्षक

-0.77

сылкі

-0.77

 createState

-0.77

("}\

-0.75

]}\

-0.75

Datuak

-0.72

IONI

-0.72

POSITIVE LOGITS

No

1.51

No

1.49

no

1.34

NO

1.31

NO

1.19

no

1.16

nof

0.99

sno

0.90

 Noyes

0.87

bno

0.87

Activations Density 0.125%

negative responses or rejections

No Comments

No Known Activations