INDEX

Explanations

phrases indicating quantities, particularly "some"

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

"Some" followed by positive words

np_acts-logits-general · gemini-2.0-flash

some and a noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

any

-0.60

steamcommunity

-0.59

 peinado

-0.54

Composable

-0.53

 VizieR

-0.53

 kaž

-0.53

 ninguna

-0.52

 totalité

-0.52

一遍

-0.52

BarStyle

-0.51

POSITIVE LOGITS

 stuff

0.91

 excitement

0.81

 nice

0.81

 CreateTagHelper

0.78

 inspiration

0.76

 laughs

0.71

fun

0.71

 goodies

0.70

 confusion

0.69

 good

0.68

Activations Density 0.253%

phrases indicating quantities, particularly "some"

"Some" followed by positive words

some and a noun

No Comments

No Known Activations