INDEX

Explanations

instances of satisfaction or dissatisfaction

oai_token-act-pair · gpt-3.5-turbo

terms related to satisfaction and fulfillment

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

planes

-0.67

sung

-0.66

olan

-0.65

plane

-0.63

 Luxem

-0.62

oss

-0.62

RN

-0.62

origin

-0.62

bold

-0.61

trop

-0.61

POSITIVE LOGITS

 Satisf

1.17

 satisfied

1.11

atisf

1.08

 satisfaction

1.08

ments

1.03

actory

1.01

 satisf

0.94

 satisfy

0.89

MENTS

0.89

 satisfies

0.89

Activations Density 0.019%

instances of satisfaction or dissatisfaction

terms related to satisfaction and fulfillment

No Comments

No Known Activations