INDEX

Explanations

references to negative effects or conditions associated with toxicity or lack of correlation 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.46

arXiv

-0.46

-0.42

“

-0.42

-0.40

Jr

-0.38

vor

-0.37

TabIndex

-0.37

POSITIVE LOGITS

afficheront

0.91

ьаж

0.88

Билгалдахарш

0.85

LookAnd

0.82

 wireType

0.80

 Administrativna

0.80

Diwedd

0.76

FailureListener

0.75

 Wikimedijinoj

0.75

ConstraintMaker

0.73

Activations Density 0.988%

references to negative effects or conditions associated with toxicity or lack of correlation in various contexts

No Comments

No Known Activations