INDEX

Explanations

information related to character traits and relationships in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

+#+#

-0.87

__':

-0.69

__':

-0.65

ьаж

-0.63

__":

-0.63

ruptedException

-0.62

expandindo

-0.60

ISupport

-0.60

extAlignment

-0.59

 متعلقه

-0.58

POSITIVE LOGITS

 hilarious

0.59

 comedy

0.55

 antics

0.55

 comedic

0.52

 shenan

0.51

 boister

0.51

 lazily

0.50

databind

0.49

 exaggerated

0.49

ÉL

0.48

Activations Density 0.204%

information related to character traits and relationships in narratives

No Comments

No Known Activations

information related to character traits and relationships in narratives

No Comments

No Known Activations