INDEX

Explanations

elements that indicate symptoms or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

versies

-0.59

ỡng

-0.58

ثيق

-0.58

ReusableCell

-0.57

ември

-0.55

Persön

-0.55

ArgsConstructor

-0.55

principalColumn

-0.53

NCIA

-0.52

TestTools

-0.51

POSITIVE LOGITS

 signs

2.44

 indications

2.13

 indication

2.12

 sign

2.02

Signs

2.01

 Signs

2.01

 indicators

2.01

signs

1.98

 signes

1.98

 signals

1.96

Activations Density 0.567%

elements that indicate symptoms or medical conditions

No Comments

No Known Activations