INDEX

Explanations

references to legal or procedural terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

%)$

-0.77

nodeValue

-0.71

))))))))

-0.71

 getView

-0.70

})()

-0.69

ukone

-0.68

 relationship

-0.67

__.

-0.67

ποτε

-0.67

 Robinson

-0.66

POSITIVE LOGITS

 за

2.00

За

1.51

za

1.48

 За

1.42

 ЗА

1.20

Za

1.17

Za

1.12

за

1.09

ZA

1.01

ЗА

0.92

Activations Density 0.022%

references to legal or procedural terminology

No Comments

No Known Activations