INDEX

Explanations

phrases related to conjunctions and logical connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ArrowToggle

-0.99

ItemBackground

-0.76

lapsingToolbar

-0.67

RTEE

-0.66

InputBorder

-0.66

principalTable

-0.65

Przypisy

-0.65

Referències

-0.64

WithMany

-0.64

-------

-0.63

POSITIVE LOGITS

 finally

0.53

 simply

0.46

 lastly

0.46

yorsunuz

0.46

 entfer

0.45

 ArrayAdapter

0.43

 ultimately

0.43

 finalmente

0.42

IENCE

0.42

setupUi

0.42

Activations Density 0.206%

phrases related to conjunctions and logical connections between ideas

No Comments

No Known Activations