INDEX

Explanations

references to the concept of "good faith."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 myſelf

-0.89

 doubtnut

-0.89

COUVER

-0.88

 Majefty

-0.86

 ISNI

-0.83

 ftate

-0.81

 Anſ

-0.79

出版年

-0.79

 defire

-0.79

Życiorys

-0.79

POSITIVE LOGITS

 good

4.76

good

4.28

Good

3.90

 Good

3.87

 GOOD

3.58

GOOD

3.46

 buena

2.77

 gute

2.62

 buenas

2.51

 buona

2.46

Activations Density 0.045%

references to the concept of "good faith."

No Comments

No Known Activations