INDEX

Explanations

elements related to programming constructs and data structures

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

Code-related tokens

np_acts-logits-general · gemini-2.0-flash

archaic English

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.67

-0.60

-0.57

“

-0.52

 aber

-0.50

he

-0.50

an

-0.50

the

-0.49

-0.48

POSITIVE LOGITS

 myſelf

1.38

 Majefty

1.32

 pleaſure

1.29

 Reſ

1.25

 Anſ

1.25

 Houſe

1.24

 Theſe

1.23

 ſever

1.20

 Monfieur

1.19

 Diſ

1.19

Activations Density 0.268%

elements related to programming constructs and data structures

Code-related tokens

archaic English

No Comments

No Known Activations