INDEX

Explanations

pieces of text signaling the beginning or end of sections and some specific references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.65

onOptions

-0.62

 abstrait

-0.57

 fréquent

-0.51

 vivre

-0.50

awtextra

-0.48

InitStruct

-0.48

 AssemblyTitle

-0.48

yntaxException

-0.48

 credere

-0.46

POSITIVE LOGITS

 other

0.77

 còn

0.66

 altres

0.65

Другие

0.62

的其他

0.61

 also

0.60

Other

0.60

OTHER

0.60

other

0.58

 Other

0.58

Activations Density 1.738%

pieces of text signaling the beginning or end of sections and some specific references

No Comments

No Known Activations