INDEX

Explanations

terms related to health and 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Mathi

-1.09

ADI

-1.07

 Dali

-1.06

 estekak

-1.03

ंदीखरीदारी

-1.02

SCI

-1.00

 Rossetti

-1.00

SSI

-1.00

TSI

-1.00

 Niki

-0.98

POSITIVE LOGITS

ness

0.87

shard

0.68

nya

0.67

Ś

0.63

 Gear

0.62

pym

0.60

Rys

0.58

 geprek

0.58

 itemView

0.58

 Sanderson

0.57

Activations Density 2.664%

terms related to health and medical conditions

No Comments

No Known Activations