INDEX

Explanations

expressions of anger or frustration, often using profanity

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

Negative or angry language

np_acts-logits-general · gemini-2.0-flash

aggressive commands or insults

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

JsonInclude

-0.45

ConstraintMaker

-0.45

']}

-0.45

:_

-0.45

חן

-0.44

]--;

-0.44

ⓧ

-0.44

bably

-0.44

 SEDS

-0.43

POSITIVE LOGITS

sizeCache

0.68

Espèce

0.67

osoba

0.67

onAttach

0.63

🖕

0.61

Shut

0.59

хь

0.59

shut

0.57

 vectorielle

0.57

 Shut

0.57

Activations Density 0.170%

expressions of anger or frustration, often using profanity

Negative or angry language

aggressive commands or insults

No Comments

No Known Activations

expressions of anger or frustration, often using profanity

Negative or angry language

aggressive commands or insults

No Comments

No Known Activations