INDEX

Explanations

phrases that indicate negation or opposition in relation to rights and social issues

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

and

-0.49

-0.44

 responsabile

-0.39

/#

-0.37

 finalmente

-0.37

komen

-0.36

anz

-0.36

hasNext

-0.36

 এবং

-0.35

 нале

-0.35

POSITIVE LOGITS

SequentialGroup

1.00

 Мексичка

0.97

ंदीखरीदारी

0.94

complexContent

0.93

MigrationBuilder

0.92

 للاسماء

0.92

protoimpl

0.90

 незавершена

0.89

 Italijanski

0.85

 InputDecoration

0.84

Activations Density 0.256%

phrases that indicate negation or opposition in relation to rights and social issues

No Comments

No Known Activations