INDEX

Explanations

terms related to eagles and tigers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

gebob

-0.60

nestjs

-0.56

 Sheeran

-0.54

OGND

-0.53

WEBPACK

-0.50

OrNil

-0.50

BNB

-0.49

 Chickens

-0.49

LAHOMA

-0.49

cellation

-0.48

POSITIVE LOGITS

 Eagle

1.37

 Tiger

1.34

Eagle

1.27

Tiger

1.20

 tiger

1.10

 eagle

1.02

 Tigers

0.98

eagle

0.91

tiger

0.90

Oak

0.83

Activations Density 0.213%

terms related to eagles and tigers

No Comments

No Known Activations