INDEX

Explanations

negative qualifiers and references to experience or expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 utafitiHapana

-0.66

Diweddarwch

-0.65

 مشين

-0.65

ésia

-0.63

Lähteet

-0.62

ibilità

-0.61

rawDesc

-0.61

tacles

-0.58

usercontent

-0.57

tacle

-0.56

POSITIVE LOGITS

MemoryWarning

0.65

BASEPATH

0.60

 kasarigan

0.59

nor

0.54

CodedInputStream

0.50

出版年

0.46

ExtendWith

0.45

inerja

0.44

 explicitly

0.44

 ***!

0.42

Activations Density 0.439%

negative qualifiers and references to experience or expertise

No Comments

No Known Activations