INDEX

Explanations

references to geometric shapes, specifically circles and related terms

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

ntax

-0.86

 pitié

-0.80

+#+

-0.79

niest

-0.77

<thead>

-0.77

 Fordham

-0.76

MenuInflater

-0.75

zczegól

-0.73

isiaj

-0.73

 Mahomet

-0.73

POSITIVE LOGITS

 Circle

2.40

 circle

2.39

 CIRCLE

2.27

 circles

2.26

Circle

2.23

 Circles

2.12

circle

2.11

CIRCLE

1.94

circles

1.93

Circles

1.92

Activations Density 0.074%

references to geometric shapes, specifically circles and related terms

No Comments

No Known Activations