INDEX

Explanations

phrases related to affirmation, recommendations, and positive evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 särsk

-0.44

今度は

-0.43

rrggbb

-0.41

 sær

-0.40

-0.39

addObject

-0.39

 justement

-0.39

گه

-0.38

),

-0.38

 thereunder

-0.37

POSITIVE LOGITS

writeFieldEnd

0.89

SharedDtor

0.85

idth

0.69

Obrázky

0.69

PageFactory

0.66

=$?

0.66

حوالہ

0.65

 дописавши

0.64

 Référence

0.63

ExecuteReader

0.62

Activations Density 0.453%

phrases related to affirmation, recommendations, and positive evaluations

No Comments

No Known Activations