INDEX

Explanations

statements of forgetfulness or the act of forgetting, particularly related to emotions and personal beliefs

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

Statements or opinions expressed using "I," "You," "He," "She," or "They."

np_acts-logits-general · gemini-2.0-flash

pronouns followed by verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

alapa

-0.48

ICKNESS

-0.47

losse

-0.46

 fermés

-0.46

Jîn

-0.45

ERING

-0.45

Throws

-0.45

hynch

-0.44

ญ

-0.44

eringer

-0.44

POSITIVE LOGITS

 ditto

0.96

 CreateTagHelper

0.91

ditto

0.86

 idem

0.83

SpringBootTest

0.75

 likewise

0.73

 επίσης

0.72

ChildScrollView

0.68

IntoConstraints

0.68

ValueStyle

0.68

Activations Density 0.303%

statements of forgetfulness or the act of forgetting, particularly related to emotions and personal beliefs

Statements or opinions expressed using "I," "You," "He," "She," or "They."

pronouns followed by verbs

No Comments

No Known Activations

statements of forgetfulness or the act of forgetting, particularly related to emotions and personal beliefs

Statements or opinions expressed using "I," "You," "He," "She," or "They."

pronouns followed by verbs

No Comments

No Known Activations