INDEX

Explanations

phrases related to decision-making and choices in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

########.

-0.52

 <=",

-0.49

QUIN

-0.48

 Preferencias

-0.47

 facture

-0.47

quin

-0.46

AfterClass

-0.46

 שוליים

-0.42

IGraphics

-0.42

Mediabestanden

-0.41

POSITIVE LOGITS

 reaſon

0.74

 itſelf

0.71

دانشنامهٔ

0.68

 myſelf

0.67

 faſt

0.65

 pleaſure

0.64

يكب

0.63

 themſelves

0.63

 fathoms

0.63

 uſe

0.63

Activations Density 0.230%

phrases related to decision-making and choices in different contexts

No Comments

No Known Activations