INDEX

Explanations

phrases expressing opinions or evaluations

oai_token-act-pair · gpt-3.5-turbo

phrases that reference comparable situations or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eteria

-0.81

ourse

-0.71

elin

-0.69

iband

-0.65

esson

-0.65

utenberg

-0.65

ells

-0.63

iven

-0.63

arate

-0.63

iets

-0.63

POSITIVE LOGITS

lihood

1.32

 ours

1.24

 hers

1.05

 yours

0.99

 theirs

0.93

pires

0.81

liest

0.77

 minded

0.73

lier

0.70

 Deng

0.68

Activations Density 0.105%

phrases expressing opinions or evaluations

phrases that reference comparable situations or events

No Comments

No Known Activations