INDEX

Explanations

terms related to legal processes and actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lit" and its variations in legal contexts

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

Downloadha

-0.78

CVE

-0.72

xus

-0.72

ä½ľ

-0.68

FactoryReloaded

-0.67

axter

-0.67

sonian

-0.66

jri

-0.65

 Sense

-0.65

 Annotations

-0.65

POSITIVE LOGITS

igated

1.10

ters

1.10

lit

1.08

urgy

1.03

igating

1.00

igators

0.97

urgical

0.97

eral

0.94

igious

0.89

terness

0.89

Activations Density 0.016%

terms related to legal processes and actions

occurrences of the word "lit" and its variations in legal contexts

No Comments

No Known Activations