INDEX

Explanations

positive affirmations and expressions of hope

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nostru

-0.70

我们在

-0.66

our

-0.63

让我们

-0.61

 saya

-0.60

 ourselves

-0.59

NameInMap

-0.58

 diyor

-0.57

apunov

-0.57

 Subsequently

-0.56

POSITIVE LOGITS

 hadn

0.89

 fucking

0.69

 goddamn

0.69

 damned

0.68

>--}}

0.67

 tonight

0.64

~*~

0.63

 stupid

0.62

 stupidly

0.62

انجليز

0.59

Activations Density 0.540%

positive affirmations and expressions of hope

No Comments

No Known Activations