INDEX

Explanations

references to physical interactions or emotional connections between individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ótica

-0.51

pheus

-0.51

لاثة

-0.50

 чем

-0.49

ที่สุด

-0.49

vrigt

-0.48

 personne

-0.47

-0.46

Na

-0.45

keywords

-0.44

POSITIVE LOGITS

 itſelf

1.11

 myſelf

0.98

 Monfieur

0.94

 himſelf

0.89

 Anſ

0.84

InputBorder

0.84

 themſelves

0.82

writeFieldEnd

0.81

Personensuche

0.78

setVerticalGroup

0.77

Activations Density 1.101%

references to physical interactions or emotional connections between individuals

No Comments

No Known Activations