INDEX

Explanations

exclamation marks and other punctuation indicating strong emotions or reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

databind

-0.87

\}\\

-0.74

}{*}{

-0.74

脚注の使い方

-0.72

fillType

-0.68

__':

-0.68

'],

-0.68

esgue

-0.67

ελ

-0.67

onnaissance

-0.67

POSITIVE LOGITS

.........

1.09

!!!!!

1.06

 enfans

1.00

?????

0.97

!!!!

0.94

 !!!!

0.92

ooooo

0.92

 !!!!!

0.90

>>>>>

0.89

 religieuses

0.87

Activations Density 0.231%

exclamation marks and other punctuation indicating strong emotions or reactions

No Comments

No Known Activations