INDEX

Explanations

references to specific names and entities, particularly in the context of academic or scientific discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ChildScrollView

-0.77

 myſelf

-0.77

 OkHttpClient

-0.74

 '\\;'

-0.73

 ProtoMessage

-0.71

Rtl

-0.70

存于互联网档案馆

-0.69

 himo

-0.68

namental

-0.68

DeleteBehavior

-0.66

POSITIVE LOGITS

djangoproject

0.70

 gran

0.55

incar

0.53

Lad

0.53

0.52

pri

0.51

 bình

0.50

anwal

0.50

les

0.50

Activations Density 0.267%

references to specific names and entities, particularly in the context of academic or scientific discussions

No Comments

No Known Activations