INDEX

Explanations

references to legal concepts and court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

RenderAtEndOf

-0.61

 defaultstate

-0.50

edicated

-0.46

LocationManager

-0.46

 rospy

-0.45

 CanadaChoose

-0.45

árbol

-0.45

entibus

-0.44

vampire

-0.44

EndGlobalSection

-0.43

POSITIVE LOGITS

 Supreme

0.51

 Justices

0.46

 justices

0.45

 beginnetje

0.45

Supreme

0.44

mergeFrom

0.44

 certiorari

0.42

 Court

0.42

supreme

0.41

 suprême

0.39

Activations Density 1.464%

references to legal concepts and court cases

No Comments

No Known Activations