INDEX

Explanations

statements or references to "this" or "that" in a contextual or definitional manner

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

"This" followed by a verb

np_acts-logits-general · gemini-2.0-flash

This followed by is/was

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

extAlignment

-0.67

CodeAttribute

-0.55

 ModelExpression

-0.55

Especies

-0.53

arResult

-0.52

RegressionTest

-0.51

หน้านี้

-0.51

RenderAtEndOf

-0.50

哦

-0.50

游戏特色

-0.49

POSITIVE LOGITS

is

0.95

was

0.85

 certainly

0.83

 means

0.81

 includes

0.79

 wasn

0.78

 begs

0.75

isn

0.71

 wiederum

0.70

may

0.70

Activations Density 0.229%

statements or references to "this" or "that" in a contextual or definitional manner

"This" followed by a verb

This followed by is/was

No Comments

No Known Activations