INDEX

Explanations

expressions related to personal experiences and sentiments

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

Adjectives before certain nouns

np_acts-logits-general · gemini-2.0-flash

a followed by a descriptive word

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

位

-0.56

DllImport

-0.56

LabelTagHelper

-0.52

äude

-0.51

ordano

-0.50

fxml

-0.50

setHorizontal

-0.50

({});

-0.49

expandindo

-0.49

 OMITBAD

-0.47

POSITIVE LOGITS

 delight

0.71

 rarity

0.68

 régal

0.66

 surpresa

0.64

 mainstay

0.63

 sorpresa

0.61

 MainAxisSize

0.61

 understatement

0.60

 bummer

0.60

 surprise

0.59

Activations Density 0.215%

expressions related to personal experiences and sentiments

Adjectives before certain nouns

a followed by a descriptive word

No Comments

No Known Activations