INDEX

Explanations

terms related to health metrics and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

blame

-0.32

 suffer

-0.29

 luta

-0.28

ķ

-0.28

Victim

-0.28

FFER

-0.28

 wcześ

-0.28

 vítimas

-0.28

ataires

-0.28

unknownFields

-0.27

POSITIVE LOGITS

 pinulongan

0.63

ThroughAttribute

0.59

 ✭✭

0.59

Rüyada

0.56

phyla

0.55

 GetEnumerator

0.54

eddable

0.54

enderror

0.54

vertible

0.52

ahalli

0.52

Activations Density 0.738%

terms related to health metrics and outcomes

No Comments

No Known Activations