INDEX

Explanations

expressions of gratitude or thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Co

-0.48

 SEDS

-0.46

literals

-0.46

onOptions

-0.46

vician

-0.46

 broadest

-0.46

Co

-0.46

 "..\..\

-0.46

 requestCode

-0.46

 Elsewhere

-0.46

POSITIVE LOGITS

 goodness

0.86

 thank

0.86

 heavens

0.83

 Thank

0.80

thank

0.80

 THANK

0.79

ReusableCell

0.79

Thank

0.77

god

0.77

THANK

0.75

Activations Density 0.018%

expressions of gratitude or thanks

No Comments

No Known Activations