INDEX

Explanations

proper nouns and names associated with locations and institutions

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

ValueStyle

-0.83

LookAnd

-0.71

IndentedString

-0.64

 transfieras

-0.62

 Superhosts

-0.62

 للمعارف

-0.60

RTEE

-0.58

ynı

-0.57

 AssemblyTitle

-0.56

出版年

-0.56

POSITIVE LOGITS

 nakalista

0.65

iços

0.56

0.55

ocios

0.52

Ży

0.51

 anytime

0.50

gypti

0.48

 which

0.47

Ent

0.47

oule

0.46

Activations Density 0.463%

proper nouns and names associated with locations and institutions

No Comments

No Known Activations