INDEX

Explanations

terms related to perspective and acknowledgment in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

+#+

-0.59

PerformLayout

-0.54

ParallelGroup

-0.54

égi

-0.52

ngdoc

-0.52

 regular

-0.50

 affaire

-0.50

лій

-0.50

cipar

-0.49

 Affiliations

-0.48

POSITIVE LOGITS

 contemplation

0.95

 contemplates

0.91

 acknowledgement

0.89

 perspective

0.89

 viewpoint

0.86

perspective

0.85

 sunglasses

0.85

 contemplate

0.84

 standpoint

0.84

 MenuView

0.82

Activations Density 0.088%

terms related to perspective and acknowledgment in various contexts

No Comments

No Known Activations