INDEX

Explanations

references to object-oriented programming concepts, particularly related to 'self'

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

 Theſe

-0.97

 katze

-0.89

 Beſ

-0.88

 ſeveral

-0.88

 Reſ

-0.84

PhysRevD

-0.83

Efq

-0.82

 Monfieur

-0.82

Eſ

-0.81

withstanding

-0.78

POSITIVE LOGITS

 self

2.13

 Self

1.61

 SELF

1.36

Self

1.25

 Selbst

1.03

 само

0.94

Selbst

0.91

 αυτο

0.89

自我

0.81

SELF

0.73

Activations Density 0.115%

references to object-oriented programming concepts, particularly related to 'self'

No Comments

No Known Activations