INDEX

Explanations

connections between various actions, claims, or concepts in legal contexts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 StatefulWidget

-0.71

 يتيمه

-0.63

Jegyzetek

-0.61

 الحره

-0.60

.*")]

-0.56

 AssemblyCulture

-0.54

AnchorTagHelper

-0.53

ORAGE

-0.53

PropertyChanged

-0.53

 كومونز

-0.52

POSITIVE LOGITS

 primarily

1.27

 mainly

1.26

 mostly

1.10

 chiefly

1.08

 principally

1.06

primarily

1.06

mainly

0.98

 largely

0.97

 Mainly

0.96

 solely

0.93

Activations Density 0.428%

connections between various actions, claims, or concepts in legal contexts

No Comments

No Known Activations