INDEX

Explanations

references to processes of description and documentation in research contexts

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

ệc

-0.55

oa̍t

-0.54

ành

-0.50

 geworden

-0.48

dering

-0.46

XmlAccessType

-0.46

LookAnd

-0.45

]=="

-0.44

IsContent

-0.44

"%"

-0.43

POSITIVE LOGITS

__(/*!

0.82

 تانيه

0.73

phem

0.69

PullParser

0.69

 للمعارف

0.65

 lamen

0.64

ChildScrollView

0.64

etCode

0.64

 detailed

0.63

 summarised

0.63

Activations Density 0.431%

references to processes of description and documentation in research contexts

No Comments

No Known Activations