INDEX

Explanations

conversational exchanges, particularly affirmations or inquiries about personal situations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 '\\;'

-0.63

 ModelRenderer

-0.50

memoized

-0.50

atihan

-0.49

 createSprite

-0.49

 étions

-0.49

ClientSize

-0.48

قد

-0.48

IBOutlet

-0.47

örté

-0.47

POSITIVE LOGITS

 okay

1.65

ok

1.62

OK

1.56

 Okay

1.46

 alright

1.46

 fine

1.42

Ok

1.38

Okay

1.36

okay

1.35

 OKAY

1.35

Activations Density 0.318%

conversational exchanges, particularly affirmations or inquiries about personal situations

No Known Activations