INDEX

Explanations

instances of medical terminology or references to disease-related studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ulemon

-0.57

ewear

-0.51

ăsp

-0.50

!("

-0.49

InputModule

-0.49

rakech

-0.48

 forKey

-0.48

nessed

-0.47

umenical

-0.47

solete

-0.46

POSITIVE LOGITS

MemoryWarning

0.91

AddTagHelper

0.88

ⓧ

0.81

<td>

0.79

/*

0.73

msgTypes

0.71

 ***!

0.71

SizeF

0.67

Rhestr

0.64

AutoScale

0.64

Activations Density 0.033%

instances of medical terminology or references to disease-related studies

No Comments

No Known Activations