INDEX

Explanations

phrases related to administrative processes and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 OFDb

-0.56

 setPrice

-0.56

 renting

-0.54

quium

-0.53

 reinstalling

-0.53

Demonstration

-0.52

autoload

-0.52

InstrumentedTest

-0.51

 copolymer

-0.51

ModelSerializer

-0.51

POSITIVE LOGITS

 processing

1.57

 processed

1.45

 Processing

1.44

Processing

1.32

 PROCESSING

1.32

processing

1.32

processed

1.20

 Processed

1.18

Processed

1.09

 procesamiento

1.04

Activations Density 0.358%

phrases related to administrative processes and documentation

No Comments

No Known Activations