INDEX

Explanations

phrases indicating levels or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

DrawerToggle

-0.60

 kasarigan

-0.60

knex

-0.55

PropertyChanging

-0.55

pulumi

-0.55

--)

-0.54

 Dostupné

-0.52

 referenties

-0.52

Puss

-0.52

colgroup

-0.51

POSITIVE LOGITS

mentioned

1.22

ground

1.07

 ground

0.84

 mentioned

0.82

👆

0.78

 ExecuteAsync

0.78

ABOVE

0.73

 ABOVE

0.72

 Mentioned

0.72

GROUND

0.71

Activations Density 0.094%

phrases indicating levels or comparisons

No Comments

No Known Activations