INDEX

Explanations

occurrences of the word "in" and its context within various phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

AnchorStyles

-0.56

addGap

-0.54

Which

-0.49

 Which

-0.49

which

-0.49

anias

-0.48

contentLoaded

-0.47

ing

-0.47

///</

-0.46

DockStyle

-0.45

POSITIVE LOGITS

GEBURTSDATUM

0.75

 anonymously

0.71

 without

0.64

 NSCoder

0.64

 seamlessly

0.62

 חיצוניים

0.59

ArrowToggle

0.58

 blindly

0.58

 quietly

0.58

 with

0.57

Activations Density 0.121%

occurrences of the word "in" and its context within various phrases

No Comments

No Known Activations