INDEX

Explanations

terms related to safety and risk assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

complexContent

-0.88

="@+

-0.72

 pró

-0.70

✨:

-0.69

 Hooper

-0.69

__":

-0.68

 MenuView

-0.67

 Wiktionnaire

-0.66

chaun

-0.65

JMenu

-0.65

POSITIVE LOGITS

SAFE

1.50

 Safe

1.50

 SAFE

1.46

 safe

1.44

Safe

1.38

 safer

1.32

safe

1.26

SAFETY

1.26

 safety

1.24

 safest

1.24

Activations Density 0.039%

terms related to safety and risk assessment

No Comments

No Known Activations