INDEX

Explanations

references to negative emotions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

matchCondition

-0.50

Tikang

-0.47

 nahilalakip

-0.44

 ویکی‌پدی

-0.44

Glej

-0.41

AsUp

-0.41

 Dzięki

-0.41

 DEMAND

-0.41

 FAVOR

-0.40

AddTagHelper

-0.40

POSITIVE LOGITS

FailureListener

0.76

ViewFeatures

0.61

NegativeButton

0.55

 onCancelled

0.54

Worse

0.53

EnableWeb

0.52

 negativo

0.52

 unfavourable

0.52

 negatives

0.51

 worst

0.50

Activations Density 1.705%

references to negative emotions and experiences

No Comments

No Known Activations