INDEX

Explanations

terms related to being contained or restricted

oai_token-act-pair · gpt-3.5-turbo

the concept of confinement or restriction in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 foundation

-0.64

soDeliveryDate

-0.62

estamp

-0.62

CF

-0.60

alky

-0.60

 ethic

-0.59

Eth

-0.59

Ily

-0.56

HRC

-0.56

df

-0.56

POSITIVE LOGITS

 confinement

1.05

 confined

0.90

untarily

0.82

ĸļ

0.79

 confines

0.77

icut

0.76

 pigeon

0.72

 nudity

0.72

 quarantine

0.71

 shack

0.70

Activations Density 0.012%

terms related to being contained or restricted

the concept of confinement or restriction in various contexts

No Comments

No Known Activations