INDEX

Explanations

references to locations and structures, particularly related to apartments, stores, and hospitals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

printStackTrace

-0.53

ActionCreators

-0.49

ânico

-0.49

cenia

-0.47

rsiniz

-0.47

 unknownFields

-0.46

AutoresizingMask

-0.46

angliski

-0.46

tigkeit

-0.46

Rptr

-0.45

POSITIVE LOGITS

 فريبيس

0.59

 Himo

0.59

bootstrapcdn

0.58

 تانيه

0.58

Tembelea

0.58

 campur

0.56

новништво

0.55

 parcheggio

0.54

 immédi

0.53

 där

0.52

Activations Density 0.999%

references to locations and structures, particularly related to apartments, stores, and hospitals

No Comments

No Known Activations