INDEX

Explanations

expressions of agreement or consensus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

OGND

-0.64

帖最后由

-0.60

 المعيارى

-0.59

fortawesome

-0.57

addGap

-0.56

[]:

-0.53

➯

-0.53

ſammen

-0.52

 oftentimes

-0.50

 pinulongan

-0.49

POSITIVE LOGITS

 agreed

1.05

agreed

1.01

 agree

0.94

 agrees

0.92

 agreement

0.92

Agreed

0.90

 Agreed

0.90

agree

0.85

 Agree

0.84

 AGRE

0.84

Activations Density 0.107%

expressions of agreement or consensus

No Comments

No Known Activations

expressions of agreement or consensus

No Comments

No Known Activations