INDEX

Explanations

keywords related to note-taking and organization

oai_token-act-pair · gpt-3.5-turbo

terms related to applications and software features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

abama

-0.80

lesiastical

-0.73

gew

-0.69

roe

-0.68

 Dise

-0.68

rish

-0.66

iminary

-0.65

HAEL

-0.65

Eug

-0.65

åħī

-0.64

POSITIVE LOGITS

 apps

1.28

 functionality

1.20

app

1.10

 sync

1.07

 APIs

1.06

 widgets

1.02

 caching

1.01

 capabilities

1.00

 mode

1.00

 synchronization

0.99

Activations Density 0.314%

keywords related to note-taking and organization

terms related to applications and software features

No Comments

No Known Activations