INDEX

Explanations

intense emotional descriptors and significant impacts of actions

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

Adjectives followed by "that"

np_acts-logits-general · gemini-2.0-flash

so... that structure

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

AddWithValue

-0.56

 consistente

-0.48

AutoField

-0.47

ients

-0.46

økt

-0.46

 препратки

-0.46

dailymail

-0.45

somewhat

-0.44

govine

-0.44

dez

-0.44

POSITIVE LOGITS

 înc

0.95

 that

0.74

 tellement

0.68

ImageContext

0.67

so

0.66

OrNil

0.66

XmlAccessorType

0.65

NameInMap

0.63

Tikang

0.62

 mogelijk

0.62

Activations Density 0.091%

intense emotional descriptors and significant impacts of actions

Adjectives followed by "that"

so... that structure

No Comments

No Known Activations