INDEX

Explanations

words related to various specific events or actions

oai_token-act-pair · gpt-3.5-turbo

terms related to actions and measurements involving significant changes or modifications

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

 Citiz

-0.57

bow

-0.48

talk

-0.47

die

-0.45

arenthood

-0.45

 goddess

-0.45

berman

-0.42

kar

-0.42

 discovery

-0.42

 skelet

-0.41

POSITIVE LOGITS

lihood

0.58

ibly

0.57

ajor

0.53

hots

0.52

 actionGroup

0.52

æ©

0.50

uggest

0.50

 Tradable

0.47

Amb

0.46

uper

0.46

Activations Density 1.106%

words related to various specific events or actions

terms related to actions and measurements involving significant changes or modifications

No Comments

No Known Activations