INDEX

Explanations

references to "case" and related terminology in legal and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Monfieur

-1.18

 Theſe

-1.13

 pleaſure

-1.11

 raiſ

-1.03

 Mercurio

-1.02

edicated

-1.02

 havaianas

-0.94

 uſed

-0.93

Děkuji

-0.93

 photolibrary

-0.91

POSITIVE LOGITS

 cases

2.40

 case

2.33

 Cases

2.13

 Case

2.13

case

2.09

Cases

2.08

cases

2.06

Case

2.04

 CASE

2.01

CASE

1.95

Activations Density 0.092%

references to "case" and related terminology in legal and medical contexts

No Comments

No Known Activations