INDEX

Explanations

instances of the word "this" and its variations as indicators of emphasis or reference

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

ConstraintMaker

-0.61

 propOrder

-0.56

 purposes

-0.54

 ovat

-0.53

Distribución

-0.52

ceedings

-0.51

²-

-0.49

llary

-0.48

Erreferentziak

-0.48

Exceeded

-0.48

POSITIVE LOGITS

########.

0.68

 lack

0.67

 laatste

0.64

 same

0.63

writeField

0.61

 desire

0.60

 reluctance

0.60

 fact

0.60

 inability

0.59

 attitude

0.59

Activations Density 0.272%

instances of the word "this" and its variations as indicators of emphasis or reference

No Comments

No Known Activations