INDEX

Explanations

instances where actions or decisions are being taken or made

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal actions and official procedures

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

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

inventoryQuantity

-0.71

ãĥ©ãĥ³

-0.65

itte

-0.61

ãģĦ

-0.56

tion

-0.55

IPM

-0.55

pop

-0.55

 Surviv

-0.54

 overe

-0.54

finished

-0.53

POSITIVE LOGITS

 whereby

0.79

 regarding

0.71

iosis

0.70

 throughout

0.70

izons

0.68

.–

0.68

ALSE

0.67

iat

0.67

.:

0.67

.):

0.65

Activations Density 0.241%

instances where actions or decisions are being taken or made

phrases related to legal actions and official procedures

No Comments

No Known Activations