INDEX

Explanations

descriptions of people, objects, and actions in specific scenarios

oai_token-act-pair · gpt-3.5-turbo

references to people or entities involved in actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

*.

-0.69

$.

-0.67

".

-0.67

!.

-0.64

%.

-0.63

'.

-0.59

 whereas

-0.57

".[

-0.57

 instead

-0.56

 accordingly

-0.56

POSITIVE LOGITS

pires

0.71

apeake

0.53

estern

0.51

MFT

0.50

pired

0.48

 Revival

0.47

 meanwhile

0.45

 Offline

0.44

actionDate

0.43

 Popular

0.43

Activations Density 1.332%

descriptions of people, objects, and actions in specific scenarios

references to people or entities involved in actions or events

No Comments

No Known Activations