INDEX

Explanations

variations of the word "full" and related phrases indicating completeness or entirety

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

Efq

-0.89

 Muses

-0.87

 Monfieur

-0.87

 itſelf

-0.87

 AppCompatTheme

-0.86

 placard

-0.85

LZ

-0.85

 ARXIV

-0.84

Mutagenicity

-0.84

 Vespa

-0.84

POSITIVE LOGITS

 Full

1.61

 full

1.55

Full

1.41

 FULL

1.39

FULL

1.32

full

1.23

 Fuller

1.13

 Voll

1.07

fullPath

1.00

Fuller

0.94

Activations Density 0.064%

variations of the word "full" and related phrases indicating completeness or entirety

No Comments

No Known Activations