INDEX

Explanations

academic departments and organizational affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Referències

-0.56

PullParser

-0.54

Przypisy

-0.54

-------------</

-0.53

LDA

-0.53

 LUMI

-0.52

 createContext

-0.52

ăn

-0.51

lottesville

-0.50

cedures

-0.50

POSITIVE LOGITS

 engineering

1.68

 Engineering

1.59

 engineers

1.52

Engineering

1.47

 engineer

1.46

engineering

1.44

 Engineers

1.44

 Engineer

1.41

Engineers

1.39

 ENGINEERING

1.39

Activations Density 0.253%

academic departments and organizational affiliations

No Comments

No Known Activations