INDEX

Explanations

references to danger and self-preservation

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

Colloquial or AAVE language

np_acts-logits-general · gemini-2.0-flash

slang and profanity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

Perhaps

-0.44

 Perhaps

-0.42

 tolle

-0.40

 perhaps

-0.39

perhaps

-0.39

 wohl

-0.38

 wonderfully

-0.35

 wonderful

-0.35

 tollen

-0.34

mittelt

-0.33

POSITIVE LOGITS

 niggas

0.94

 nigga

0.85

 tryna

0.79

 motherfucker

0.79

ain

0.75

 homie

0.73

 hella

0.67

 fuckin

0.67

 shit

0.66

 fuck

0.65

Activations Density 0.172%

references to danger and self-preservation

Colloquial or AAVE language

slang and profanity

No Comments

No Known Activations