INDEX

Explanations

phrases related to responsibility and accountability in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 showcasing

-0.83

 showcased

-0.79

 transitioning

-0.75

Mhm

-0.74

 incentiv

-0.73

FYI

-0.73

 MULTIPLE

-0.72

 specifik

-0.71

klart

-0.71

 grandkids

-0.71

POSITIVE LOGITS

 doubtless

0.66

 such

0.64

 there

0.58

we

0.56

 indeed

0.56

 persons

0.55

 thereupon

0.55

 yalnız

0.51

 freilich

0.51

 skall

0.50

Activations Density 0.610%

phrases related to responsibility and accountability in various contexts

No Comments

No Known Activations