INDEX

Explanations

terms related to extraction and purification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

WithMany

-0.77

ControllerAdvice

-0.61

TypeDef

-0.59

UnitTesting

-0.59

setArguments

-0.58

 onOptions

-0.58

IZEN

-0.57

Caprio

-0.57

 useNavigate

-0.56

complexContent

-0.56

POSITIVE LOGITS

 extraction

1.11

 extracted

1.02

 Extraction

1.01

 extracts

0.98

 removal

0.96

 Removes

0.95

 extract

0.95

 Removal

0.94

 removed

0.94

 extracting

0.93

Activations Density 0.441%

terms related to extraction and purification processes

No Comments

No Known Activations