INDEX

Explanations

expressions of uncertainty and questions regarding decisions or beliefs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 téléphonique

-0.58

extAlignment

-0.56

__((

-0.53

 verdaderas

-0.50

 himself

-0.50

リート

-0.50

 بيها

-0.49

 paysage

-0.49

 scatola

-0.48

 chiens

-0.48

POSITIVE LOGITS

Portale

0.71

ingeki

0.69

 nahilalakip

0.66

?!?

0.64

 незавершена

0.56

TALL

0.56

دانشنامهٔ

0.55

ametros

0.54

 Roskov

0.54

?…

0.54

Activations Density 0.193%

expressions of uncertainty and questions regarding decisions or beliefs

No Comments

No Known Activations