INDEX

Explanations

references to authenticity and legitimacy

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 nakalista

-0.78

ệ

-0.58

UnknownFieldSet

-0.58

ậy

-0.57

ButterKnife

-0.55

Dreaming

-0.55

 Minaj

-0.54

 beginnetje

-0.53

 Kepler

-0.52

fetera

-0.52

POSITIVE LOGITS

 genuine

2.69

genuine

2.47

Genuine

2.40

 Genuine

2.38

 genuinely

1.93

 genu

1.88

 legitimate

1.71

 authentic

1.70

 sincere

1.63

 legitimately

1.62

Activations Density 0.097%

references to authenticity and legitimacy

No Comments

No Known Activations