INDEX

Explanations

instances of the term "self" and its derivatives in various contexts

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

OGND

-0.89

DockStyle

-0.63

 MessageBoxIcon

-0.60

queryInterface

-0.59

:✨

-0.55

UrlResolution

-0.54

])):

-0.53

__':

-0.52

coltura

-0.52

WebElementEntity

-0.52

POSITIVE LOGITS

 Self

0.93

 SELF

0.90

Self

0.83

 self

0.82

SELF

0.78

self

0.68

 setInterval

0.57

destruct

0.53

 explanatory

0.52

SEL

0.50

Activations Density 0.082%

instances of the term "self" and its derivatives in various contexts

No Comments

No Known Activations