INDEX

Explanations

expressions indicating hypothetical situations or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Personensuche

-0.69

 &___

-0.66

SharedDtor

-0.65

RegistryLite

-0.63

 '\\;'

-0.59

TagMode

-0.57

 Chwiliwch

-0.56

hyrchwyd

-0.56

mybatisplus

-0.55

RTGC

-0.55

POSITIVE LOGITS

Would

0.44

 Would

0.43

would

0.42

 Sünde

0.38

 WOULD

0.37

 would

0.36

 nhiệt

0.36

 soins

0.35

 gustaría

0.35

 hukuman

0.35

Activations Density 0.148%

expressions indicating hypothetical situations or conditions

No Comments

No Known Activations