INDEX

Explanations

expressions of gladness and appreciation

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

"Glad" followed by a personal pronoun

np_acts-logits-general · gemini-2.0-flash

expressing gladness or relief

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Enders

-0.53

 Zapo

-0.49

 viol

-0.48

 Arend

-0.47

Jeg

-0.47

 uiter

-0.45

 irresistible

-0.44

Acc

-0.44

المناصب

-0.43

 Unclassified

-0.43

POSITIVE LOGITS

 noqa

0.74

 '\\;'

0.67

SourceChecksum

0.66

principalTable

0.64

 ProtoMessage

0.64

umab

0.61

StoryboardSegue

0.60

Geplaatst

0.60

 Wicidata

0.59

पया

0.58

Activations Density 0.119%

expressions of gladness and appreciation

"Glad" followed by a personal pronoun

expressing gladness or relief

No Comments

No Known Activations