INDEX

Explanations

references to unnamed or anonymous entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setVerticalGroup

-0.66

TagMode

-0.64

QMetaType

-0.61

LookAnd

-0.61

enterOuterAlt

-0.52

 OFDb

-0.51

>{@

-0.48

ThroughAttribute

-0.48

CppMethod

-0.47

舺

-0.47

POSITIVE LOGITS

 anonymous

1.52

 nameless

1.43

 unnamed

1.36

 unidentified

1.34

 unknown

1.31

 Unknown

1.24

 anonymity

1.24

 Anonymous

1.24

 mystery

1.21

 anonyme

1.18

Activations Density 0.345%

references to unnamed or anonymous entities

No Comments

No Known Activations