INDEX

Explanations

words related to legal terminology and court references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ритори

-0.63

 архивлан

-0.62

Vidite

-0.61

abestanden

-0.58

WriteBarrier

-0.58

 يتيمه

-0.58

 كومونز

-0.56

ValueStyle

-0.55

sizeCache

-0.55

ositol

-0.55

POSITIVE LOGITS

ADATA

0.57

 ſte

0.56

ുകൾ

0.56

ONOM

0.55

Politik

0.55

 ſmall

0.54

trab

0.54

 untreated

0.54

presso

0.54

去吧

0.53

Activations Density 1.652%

words related to legal terminology and court references

No Comments

No Known Activations