INDEX

Explanations

titles of movies or music in quotation marks

oai_token-act-pair · gpt-3.5-turbo

quoted phrases or sentences

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

²¾

-0.78

ife

-0.70

mares

-0.70

senal

-0.70

ason

-0.69

thur

-0.68

mber

-0.67

cha

-0.65

ĻĤ

-0.64

acas

-0.63

POSITIVE LOGITS

/"

0.87

SPONSORED

0.81

 referring

0.79

 meaning

0.77

 implying

0.75

aka

0.74

 according

0.71

 referencing

0.71

 which

0.70

 whereby

0.69

Activations Density 0.090%

titles of movies or music in quotation marks

quoted phrases or sentences

No Comments

No Known Activations