INDEX

Explanations

transport-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to qualifications or attributes of entities

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

enegger

-0.56

 Aires

-0.52

ONEY

-0.52

schild

-0.48

aida

-0.47

retty

-0.46

$$$$

-0.45

accompan

-0.45

KEY

-0.45

hovah

-0.45

POSITIVE LOGITS

tenance

0.68

lihood

0.56

osterone

0.55

ruction

0.55

terday

0.55

ption

0.53

quartered

0.53

othing

0.52

ivery

0.50

etheless

0.49

Activations Density 0.350%

transport-related terms

terms related to qualifications or attributes of entities

No Comments

No Known Activations