INDEX

Explanations

information related to measurements and dimensions

oai_token-act-pair · gpt-3.5-turbo

numerical specifications and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 scapego

-0.81

 reneg

-0.74

 unwitting

-0.73

rompt

-0.70

 tainted

-0.69

haps

-0.68

 pund

-0.67

xit

-0.67

quit

-0.66

fav

-0.65

POSITIVE LOGITS

 diameter

1.17

 Width

1.16

 circumference

1.15

 Length

1.06

 thickness

1.05

 Weight

1.04

 Height

1.03

 height

1.02

 weighs

1.01

 Capacity

1.01

Activations Density 0.218%

information related to measurements and dimensions

numerical specifications and dimensions

No Comments

No Known Activations