INDEX

Explanations

greetings and introductions in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 tackled

-0.48

<>(

-0.45

llary

-0.44

merking

-0.43

 leap

-0.42

erey

-0.42

ற்ற

-0.42

subplots

-0.41

ariki

-0.41

onu

-0.41

POSITIVE LOGITS

 bienvenue

0.85

Welcome

0.81

ValueStyle

0.80

 Welcome

0.80

 WELCOME

0.76

 welcome

0.74

我是

0.73

welcome

0.73

WELCOME

0.72

ंदीखरीदारी

0.72

Activations Density 0.148%

greetings and introductions in text

No Comments

No Known Activations