INDEX

Explanations

events or occurrences in a temporal sequence

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

à©

-0.77

oaded

-0.72

enf

-0.72

umeric

-0.71

 Cosponsors

-0.70

ographical

-0.69

obiles

-0.68

urses

-0.68

nown

-0.67

farious

-0.67

POSITIVE LOGITS

 Hurricane

0.97

 Katrina

0.94

noon

0.85

 launch

0.84

 disasters

0.81

 Election

0.80

 fateful

0.80

 collapse

0.78

 Sept

0.77

 Christmas

0.77

Activations Density 0.170%

events or occurrences in a temporal sequence

No Comments

No Known Activations