INDEX

Explanations

references to specific names and terms related to law and legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

hen

-0.37

 bare

-0.34

key

-0.33

get

-0.32

 esfuerzan

-0.31

eğ

-0.30

bare

-0.30

ge

-0.30

hline

-0.30

div

-0.30

POSITIVE LOGITS

CloseOperation

0.98

ArrowToggle

0.88

Autoritní

0.87

ⓧ

0.84

tvguidetime

0.83

HomeAsUpEnabled

0.81

dymyr

0.79

MethodManager

0.79

ViewImports

0.79

 ostavi

0.79

Activations Density 0.238%

references to specific names and terms related to law and legal cases

No Comments

No Known Activations