INDEX

Explanations

phrases that express difficulty or challenges faced by specific roles or tasks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-0.55

TagMode

-0.54

 niyang

-0.51

ttemberg

-0.49

halation

-0.48

AndEndTag

-0.48

OGND

-0.48

oyan

-0.47

 comp

-0.47

archiviato

-0.47

POSITIVE LOGITS

 even

0.81

Even

0.74

even

0.73

 zelfs

0.72

SharedCtor

0.66

 anche

0.66

 persino

0.63

 Even

0.62

 даже

0.62

 sogar

0.60

Activations Density 0.321%

phrases that express difficulty or challenges faced by specific roles or tasks

No Comments

No Known Activations