INDEX

Explanations

phrases related to laws and legal contexts, specifically regarding state and federal laws

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations and contexts involving laws or governance

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

enegger

-0.62

milo

-0.59

apego

-0.56

acebook

-0.55

uilt

-0.54

oaded

-0.53

Tags

-0.52

urat

-0.51

Sov

-0.50

addafi

-0.47

POSITIVE LOGITS

 guise

0.71

 nutshell

0.67

 context

0.65

 circles

0.63

 vicinity

0.63

 manner

0.60

 hurry

0.59

 midst

0.59

 area

0.57

 direction

0.55

Activations Density 0.884%

phrases related to laws and legal contexts, specifically regarding state and federal laws

references to geographical locations and contexts involving laws or governance

No Comments

No Known Activations