INDEX

Explanations

phrases indicating denial or negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Италијани

-0.52

cupine

-0.46

BorderFactory

-0.45

WithIOException

-0.44

Попис

-0.42

SubMenu

-0.41

 Kombat

-0.40

 getResources

-0.39

 ridurre

-0.38

 избежать

-0.38

POSITIVE LOGITS

 ब्रेकडाउन

0.43

<?

0.41

(!__

0.39

 Missing

0.39

 missing

0.39

SequentialGroup

0.39

Missing

0.38

Ự

0.37

0.36

Activations Density 0.960%

phrases indicating denial or negation

No Comments

No Known Activations