INDEX

Explanations

phrases related to business models and associated risks

oai_token-act-pair · gpt-3.5-turbo

discussions about business models

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

 blot

-0.76

 needles

-0.73

versive

-0.69

©¶æ

-0.68

 Hubble

-0.66

Ö¼

-0.66

 Redd

-0.64

 stret

-0.64

 Resurrection

-0.62

 Finn

-0.62

POSITIVE LOGITS

uay

0.78

INESS

0.77

hips

0.75

ystem

0.75

indust

0.74

utra

0.71

OUP

0.68

hops

0.68

 academia

0.68

merce

0.67

Activations Density 0.244%

phrases related to business models and associated risks

discussions about business models

No Comments

No Known Activations