INDEX

Explanations

words related to personal or shared experiences

oai_token-act-pair · gpt-3.5-turbo

references to personal experiences

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

 annex

-0.71

vous

-0.68

yright

-0.67

nod

-0.66

sub

-0.65

law

-0.64

corn

-0.64

roup

-0.63

inately

-0.63

cut

-0.62

POSITIVE LOGITS

 experiences

1.02

 firsthand

0.97

 experience

0.90

 Experience

0.89

 experien

0.85

 Exper

0.78

iences

0.76

 abroad

0.72

Experience

0.72

ional

0.72

Activations Density 0.029%

words related to personal or shared experiences

references to personal experiences

No Comments

No Known Activations