INDEX

Explanations

words related to projects or initiatives that are in the process of being developed or executed

oai_token-act-pair · gpt-3.5-turbo

terms related to processes of development and construction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

adv

-0.66

 Patri

-0.64

ortun

-0.61

trip

-0.59

att

-0.59

elo

-0.58

quickShipAvailable

-0.58

 Caps

-0.57

Chuck

-0.56

OPS

-0.56

POSITIVE LOGITS

terday

0.90

lain

0.73

Ø©

0.68

 form

0.66

 indefinitely

0.64

 advis

0.63

 worldwide

0.62

iaries

0.62

 replacements

0.61

 awaiting

0.61

Activations Density 0.101%

words related to projects or initiatives that are in the process of being developed or executed

terms related to processes of development and construction

No Comments

No Known Activations