INDEX

Explanations

phrases related to legal matters, specifically mentioning plaintiffs

oai_token-act-pair · gpt-3.5-turbo

references to legal plaintiffs in a case

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apo

-0.77

OVA

-0.73

apes

-0.73

lasses

-0.73

ollo

-0.72

[|

-0.72

olls

-0.69

upuncture

-0.68

icrobial

-0.68

ahime

-0.66

POSITIVE LOGITS

iffs

0.88

 plaintiffs

0.87

 suing

0.81

 plaintiff

0.76

arge

0.74

 alleges

0.70

 allege

0.68

 alleging

0.68

\'

0.67

 sued

0.66

Activations Density 0.013%

phrases related to legal matters, specifically mentioning plaintiffs

references to legal plaintiffs in a case

No Comments

No Known Activations