INDEX

Explanations

references to specific individuals, names, and unique terminology related to scientific or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

provoking

-0.54

withIdentifier

-0.53

таратура

-0.53

сель

-0.51

piel

-0.50

⁩

-0.49

 CURLOPT

-0.48

papi

-0.47

 planète

-0.46

Hozzáférés

-0.46

POSITIVE LOGITS

Ash

0.65

 فريبيس

0.65

WebControls

0.63

 Waray

0.63

ash

0.63

Ash

0.62

 onAnimation

0.58

ash

0.58

ASH

0.57

 &___

0.57

Activations Density 2.613%

references to specific individuals, names, and unique terminology related to scientific or legal contexts

No Comments

No Known Activations