INDEX

Explanations

references to legal terminology 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

RETT

-0.38

ERING

-0.36

 remission

-0.36

ATOS

-0.36

ide

-0.36

ANDE

-0.35

Gweler

-0.35

ABETH

-0.35

 کاری

-0.35

Buster

-0.34

POSITIVE LOGITS

 '\\;'

0.64

awaiter

0.60

aarrggbb

0.58

 kasarigan

0.57

 CreateTagHelper

0.54



0.50

jsonwebtoken

0.49

esModule

0.48

Manbalar

0.47

awtextra

0.47

Activations Density 0.810%

references to legal terminology and court cases

No Comments

No Known Activations