INDEX

Explanations

mentions of "object" and its variants

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

SequentialGroup

-0.52

 nahilalakip

-0.49

 pinulongan

-0.46

transQ

-0.46

sizeCache

-0.43

 kiệm

-0.42

 Marín

-0.41

şiv

-0.41

SharedDtor

-0.40

 honorable

-0.40

POSITIVE LOGITS

 object

3.80

 objects

3.14

 Object

3.05

 OBJECT

2.89

 Objects

2.80

Object

2.66

object

2.66

 objeto

2.55

objects

2.44

 objet

2.44

Activations Density 0.112%

mentions of "object" and its variants

No Comments

No Known Activations

mentions of "object" and its variants

No Comments

No Known Activations