INDEX

Explanations

phrases indicating exceptions or unique cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

WillAppear

-0.91

tagHelperRunner

-0.80

IndentedString

-0.75

SourceChecksum

-0.74

$.

-0.69

 useAppContext

-0.68

MemoryWarning

-0.68

 pleaſure

-0.67

 ་་

-0.66

TargetException

-0.66

POSITIVE LOGITS

XmlAccessType

0.58

 <<<<<<<<<<<<<<

0.55

0.51

 MERCHANTABILITY

0.48

0.47

Hochspringen

0.46

Its

0.45

外部リンク

0.45

뀜

0.44

SOUNDBITE

0.44

Activations Density 1.236%

phrases indicating exceptions or unique cases

No Comments

No Known Activations