INDEX

Explanations

specific terms and phrases related to medical or clinical trial data and substance effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

__(/*!

-0.69

IBOutlet

-0.67

 BoxDecoration

-0.65

 الرياضيه

-0.59

saraba

-0.57

 Lakeside

-0.57

ConstraintMaker

-0.57

mobileqq

-0.57

PMailer

-0.55

AnchorStyles

-0.53

POSITIVE LOGITS

ab

3.32

Ab

3.18

Ab

3.00

AB

2.78

ab

2.68

AB

2.48

Abs

2.12

 Abby

2.06

 Аб

2.05

 аб

1.96

Activations Density 0.285%

specific terms and phrases related to medical or clinical trial data and substance effects

No Comments

No Known Activations