INDEX

Explanations

terms related to legal appeals and appellant cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

DoubleQuotes

-0.64

mago

-0.60

KEYCODE

-0.57

tagHelper

-0.57

 alrededores

-0.56

arko

-0.55

Tembelea

-0.54

UARIO

-0.54

্দ

-0.54

hopped

-0.53

POSITIVE LOGITS

 appeal

1.03

 Appeal

0.96

 occasion

0.91

appeal

0.90

 APPEAL

0.88

Appeal

0.86

AndEndTag

0.78

 immun

0.72

driver

0.71

 occasions

0.71

Activations Density 0.072%

terms related to legal appeals and appellant cases

No Comments

No Known Activations