INDEX

Explanations

names and specific identifiable entities, likely related to people or authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 étoit

-0.63

 pouvoit

-0.63

 auroit

-0.62

 Ordovician

-0.61

fillType

-0.59

 feroit

-0.58

 eût

-0.58

DateTimeField

-0.56

 neceſſ

-0.56

 plagioclase

-0.56

POSITIVE LOGITS

AddTagHelper

0.73

enterOuterAlt

0.58

 للمعارف

0.55

drawal

0.49

◄

0.48

&&

0.47

 שלי

0.45

LEADING

0.45

 money

0.45

linge

0.44

Activations Density 0.336%

names and specific identifiable entities, likely related to people or authors

No Comments

No Known Activations