INDEX

Explanations

terms related to scientific discovery and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 itſelf

-0.72

MimeType

-0.67

못

-0.64

 ویکی‌پدیا

-0.59

 mecán

-0.58

 Normdatei

-0.58

itself

-0.58

 florales

-0.57

})));

-0.57

strains

-0.56

POSITIVE LOGITS

 themselves

1.71

themselves

1.42

Their

1.40

 Their

1.38

 their

1.34

their

1.14

 THEIR

1.13

 they

1.10

 They

1.05

They

0.97

Activations Density 0.883%

terms related to scientific discovery and its implications

No Comments

No Known Activations