INDEX

Explanations

key concepts and terminologies related to specific topics or fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

]<<"

-0.73

 betweenstory

-0.70

UnusedPrivate

-0.69

 بيها

-0.62

Демографія

-0.62

?>>

-0.58

ffine

-0.56

PCS

-0.55

Subview

-0.54

ruch

-0.53

POSITIVE LOGITS

 صوتيه

0.61

ٌ

0.60

 scolaires

0.59

 geworden

0.59

rungsseite

0.56

onghi

0.55

ものです

0.54

的一部分

0.54

 intellectuelle

0.52

 ordinaire

0.50

Activations Density 0.794%

key concepts and terminologies related to specific topics or fields

No Comments

No Known Activations