INDEX

Explanations

references to collective pronouns and relationships between people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

ActionCreators

-0.60

 BoxFit

-0.56

TagMode

-0.56

 feroit

-0.54

 myſelf

-0.53

circling

-0.53

Efq

-0.52

UseVisualStyle

-0.52

 vixion

-0.51

 enfans

-0.51

POSITIVE LOGITS

’

0.67

are

0.63

0.62

is

0.45

 also

0.44

 simply

0.43

 actually

0.43

 basically

0.41

 currently

0.41

 essentially

0.40

Activations Density 0.575%

references to collective pronouns and relationships between people

No Comments

No Known Activations