INDEX

Explanations

instances of the word "attack" and its variations

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

{~

-0.74

 much

-0.61

 beliebt

-0.61

 whole

-0.61

Ав

-0.61

gu

-0.61

RUNTIME

-0.60

ύ

-0.57

गु

-0.56

 թվական

-0.55

POSITIVE LOGITS

 Attack

1.75

 ATTACK

1.65

 attack

1.64

 attacks

1.59

 Attacks

1.57

ATTACK

1.56

attack

1.55

Attacks

1.53

attacks

1.48

Attack

1.44

Activations Density 0.072%

instances of the word "attack" and its variations

No Comments

No Known Activations