INDEX

Explanations

references to foundational principles or criteria underlying a topic

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 purpoſe

-0.93

 Monfieur

-0.88

 pleaſure

-0.85

Efq

-0.81

 houſe

-0.80

 itſelf

-0.80

 Jefus

-0.80

 Chriftian

-0.78

 faſt

-0.78

 habet

-0.77

POSITIVE LOGITS

dientemente

0.78

μφωνα

0.75

исленность

0.62

 aufgrund

0.61

Portail

0.61

]<<

0.61

 través

0.59

 учетом

0.59

makeText

0.57

of

0.56

Activations Density 0.636%

references to foundational principles or criteria underlying a topic

No Comments

No Known Activations