INDEX

Explanations

instances of the word "so" that indicate cause and effect relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

تقاوى

-0.70

LookAnd

-0.68

 RIPRODUZIONE

-0.62

 gynhyrchwyd

-0.60

 cherchés

-0.60

 Reſ

-0.59

makeConstraints

-0.56

 pourtant

-0.55

 définiti

-0.55

ształ

-0.54

POSITIVE LOGITS

ahuila

0.62

NullException

0.60

 doGet

0.57

 farlo

0.56

 hacerlo

0.55

licola

0.54

djangoproject

0.54

weds

0.54

numerusform

0.54

oneofs

0.53

Activations Density 0.151%

instances of the word "so" that indicate cause and effect relationships

No Comments

No Known Activations