INDEX

Explanations

terms related to neutrality 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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

">//

-0.64

PRNewswire

-0.64

MigrationBuilder

-0.62

 Réponses

-0.61

出版年

-0.60

 ujednoznacz

-0.60

 متعلقه

-0.60

PerformLayout

-0.60

 peč

-0.59

+#+

-0.58

POSITIVE LOGITS

bow

0.66

 emerged

0.59

 Emerging

0.57

Становништво

0.56

Cam

0.56

 emer

0.56

 Collection

0.55

 EMER

0.55

 emerging

0.55

 émer

0.55

Activations Density 0.148%

terms related to neutrality in various contexts

No Comments

No Known Activations