INDEX

Explanations

terms related to countries and geographical regions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itures

-0.84

ovo

-0.75

ipeg

-0.71

umers

-0.71

iture

-0.71

umer

-0.69

wcs

-0.69

umerable

-0.65

ervative

-0.64

igr

-0.62

POSITIVE LOGITS

cock

0.94

gie

0.90

psy

0.84

rics

0.82

bowl

0.81

glers

0.79

ĳå£«

0.79

wig

0.77

puff

0.76

gins

0.76

Activations Density 0.023%

terms related to countries and geographical regions

No Comments

No Known Activations