INDEX

Explanations

elements related to governance and legal language

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

ending in "ed"

np_acts-logits-general · gemini-2.0-flash

past tense verb endings

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

pulumi

-0.84

 TestBed

-0.71

Hozzáférés

-0.67

mybatisplus

-0.64

]$}

-0.64

IDATE

-0.63

initializeApp

-0.62

CompilerServices

-0.61

WriteBarrier

-0.61

GARET

-0.61

POSITIVE LOGITS

ed

3.34

ED

1.96

ized

1.55

ated

1.48

ted

1.30

edly

1.18

ned

1.17

ened

1.10

ged

1.00

led

0.98

Activations Density 0.488%

elements related to governance and legal language

ending in "ed"

past tense verb endings

No Comments

No Known Activations