INDEX

Explanations

references to the concept of "full" or "complete" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 meille

-0.71

+#+

-0.64

 Monfieur

-0.63

phene

-0.63

 Wicidata

-0.61

IndentedString

-0.61

 eventType

-0.60

 vivement

-0.58

 itſelf

-0.58

 Ferne

-0.58

POSITIVE LOGITS

 full

1.34

 Full

1.34

Full

1.21

 FULL

1.17

FULL

1.13

full

1.07

 Voll

0.86

isFull

0.83

fledged

0.81

 fled

0.78

Activations Density 0.101%

references to the concept of "full" or "complete" in various contexts

No Comments

No Known Activations