INDEX

Explanations

phrases related to global situations and settings

oai_token-act-pair · gpt-3.5-turbo

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

other

-0.69

hee

-0.66

fire

-0.65

Pack

-0.64

 Feather

-0.63

 Packs

-0.61

Buy

-0.61

Wallet

-0.60

FILE

-0.59

PCB

-0.58

POSITIVE LOGITS

 unch

0.90

 "$:/

0.78

enhagen

0.77

htaking

0.76

 ourselves

0.74

phabet

0.71

EStream

0.68

 reckoning

0.68

rast

0.67

 witnessing

0.66

Activations Density 0.289%

phrases related to global situations and settings

No Comments

No Known Activations