INDEX

Explanations

evidence and indicators in discussions to assess attitudes or behaviors

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

}));

-0.61

 Vikipedi

-0.52

rond

-0.50

Malley

-0.49

 rencontr

-0.48

 Hopf

-0.47

évaluateur

-0.47

 Normdatei

-0.47

Fuse

-0.46

RenderAtEndOf

-0.45

POSITIVE LOGITS

 indicate

0.97

 indication

0.95

 indicates

0.94

 indicative

0.92

 indicating

0.91

 reflects

0.88

 demonstrates

0.83

 signify

0.81

 reflect

0.81

 menunjukkan

0.81

Activations Density 0.465%

evidence and indicators in discussions to assess attitudes or behaviors

No Comments

No Known Activations