INDEX

Explanations

terms related to the ear and hearing 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ographia

-0.54

chauffer

-0.54

TLS

-0.53

BARA

-0.52

țiunea

-0.51

 Mifflin

-0.49

miert

-0.49

romyalgia

-0.49

jectories

-0.47

gir

-0.47

POSITIVE LOGITS

ear

2.00

 ears

1.82

Ear

1.65

 Ears

1.60

Ear

1.55

 oreille

1.34

👂

1.30

ear

1.27

 oreilles

1.25

EAR

1.23

Activations Density 0.306%

terms related to the ear and hearing conditions

No Comments

No Known Activations