INDEX

Explanations

references to personal relationships and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

untut

-0.38

 chwili

-0.38

เขา

-0.37

 heet

-0.37

希望能

-0.37

setFocus

-0.37

 चाहता

-0.36

他要

-0.36

 Schwerpunkt

-0.36

他知道

-0.36

POSITIVE LOGITS

featureID

0.77

AndEndTag

0.70

 yourselves

0.63

 yourself

0.60

تقاوى

0.58

Personendaten

0.57

picasso

0.55

 configureStore

0.54

BeginContext

0.52

UnknownFieldSet

0.52

Activations Density 0.340%

references to personal relationships and interactions

No Comments

No Known Activations