INDEX

Explanations

expressions of appreciation and gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

rawQuery

-0.69

 death

-0.65

Mog

-0.64

agan

-0.63

füh

-0.62

 bact

-0.62

ModelForm

-0.61

 Death

-0.61

 muerte

-0.61

ext

-0.61

POSITIVE LOGITS

 appreciate

1.83

 Appreciate

1.70

reciate

1.64

 appreciation

1.64

 appreci

1.62

 appreciates

1.61

Appreciate

1.60

 appreciated

1.58

 appreciating

1.52

reciation

1.49

Activations Density 0.031%

expressions of appreciation and gratitude

No Comments

No Known Activations