INDEX

Explanations

statements indicating the existence or presence of concepts or phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 незавершена

-0.74

MLLoader

-0.72

 purpoſe

-0.65

LNB

-0.63

 Greeks

-0.61

OSM

-0.60

 Philist

-0.60

 Yunus

-0.59

 Sixt

-0.58

 Picchu

-0.58

POSITIVE LOGITS

the

0.87

 those

0.83

those

0.64

 aquellos

0.63

 aqueles

0.62

 celui

0.58

 aquellas

0.55

 jenes

0.55

though

0.53

 Those

0.53

Activations Density 0.236%

statements indicating the existence or presence of concepts or phenomena

No Comments

No Known Activations