INDEX

Explanations

phrases and terms related to regulation, evidence, and outcomes in legal contexts

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

exceeding a limit

np_acts-logits-general · gemini-2.0-flash

beyond limits

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 CreateTagHelper

-0.78

 فريبيس

-0.75

 MainAxisSize

-0.59

下载附件

-0.56

setVerticalGroup

-0.55

awakeFromNib

-0.53

 AssemblyCompany

-0.52

EndContext

-0.51

HtmlAttribute

-0.50

kena

-0.49

POSITIVE LOGITS

 beyond

3.23

beyond

2.87

 Beyond

2.69

 past

2.59

 BEYOND

2.56

Beyond

2.54

past

2.14

Past

2.07

 Past

2.05

 PAST

1.88

Activations Density 0.475%

phrases and terms related to regulation, evidence, and outcomes in legal contexts

exceeding a limit

beyond limits

No Comments

No Known Activations