INDEX

Explanations

evaluative language concerning creative works, focusing on their execution and impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

fillType

-0.59

তথ্যসূত্র

-0.57

DockStyle

-0.55

ワイイ

-0.52

ựng

-0.52

 متعلقه

-0.51

مقد

-0.47

ernan

-0.47

 setCode

-0.47

 getDescription

-0.47

POSITIVE LOGITS

 involving

0.67

 original

0.64

 engaging

0.63

 fresh

0.63

 organic

0.56

 coinvol

0.56

 frische

0.55

 fluid

0.55

IsContent

0.55

ègre

0.55

Activations Density 0.232%

evaluative language concerning creative works, focusing on their execution and impact

No Comments

No Known Activations