INDEX

Explanations

personal pronouns indicating groups of people

oai_token-act-pair · gpt-3.5-turbo

pronouns indicating groups of people and their experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Contents

-0.73

 appellant

-0.72

 âĢ

-0.69

ÂłÂłÂłÂł

-0.67

 ï¿½

-0.63

!!

-0.62

~~~~

-0.62

..

-0.59

OME

-0.58

Letter

-0.58

POSITIVE LOGITS

'll

1.79

're

1.64

'd

1.55

've

1.52

'm

1.31

ain

1.07

's

1.03

 hasn

1.01

't

0.99

 shouldn

0.92

Activations Density 0.643%

personal pronouns indicating groups of people

pronouns indicating groups of people and their experiences

No Comments

No Known Activations