INDEX

Explanations

references to method calls or actions in programming contexts

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

 contextLoads

-0.88

 ་་

-0.86

theless

-0.81

 NDEBUG

-0.79

Зноскі

-0.79

 itſelf

-0.78

esterday

-0.77

BibitemShut

-0.72

phrine

-0.72

Répondre

-0.72

POSITIVE LOGITS

To

1.70

TO

1.62

to

1.58

TO

1.56

To

1.56

to

1.38

Toh

1.10

uto

1.07

DataTo

1.02

tos

0.99

Activations Density 0.165%

references to method calls or actions in programming contexts

No Comments

No Known Activations