INDEX

Explanations

terms related to legal processes and scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

mybatisplus

-0.64

 чтоб

-0.63

RegressionTest

-0.58

sizeCache

-0.57

 serem

-0.57

 afin

-0.57

 provocando

-0.56

JNIEnv

-0.55

клопе

-0.54

Hochspringen

-0.54

POSITIVE LOGITS

is

2.02

has

1.73

was

1.63

 will

1.48

may

1.38

 would

1.37

can

1.35

 might

1.34

 could

1.30

 cannot

1.29

Activations Density 5.043%

terms related to legal processes and scientific research

No Comments

No Known Activations