INDEX

Explanations

instances where satisfaction is expressed or implied

oai_token-act-pair · gpt-3.5-turbo

expressions related to satisfaction and dissatisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

olan

-0.81

age

-0.75

ade

-0.69

 Attacks

-0.67

 Throw

-0.65

 Torch

-0.64

ansk

-0.64

kid

-0.60

ker

-0.60

ansom

-0.59

POSITIVE LOGITS

 satisfied

3.94

 dissatisfied

2.03

 Satisf

1.99

 pleased

1.81

 satisfaction

1.80

 fulfilled

1.76

 satisfy

1.76

atisf

1.69

 satisfies

1.63

 unsatisf

1.58

Activations Density 0.018%

instances where satisfaction is expressed or implied

expressions related to satisfaction and dissatisfaction

No Comments

No Known Activations