INDEX

Explanations

phrases related to success and achievement

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 altercation

-0.68

 clutter

-0.65

 desks

-0.63

sod

-0.62

 chairs

-0.62

 trapping

-0.61

CoC

-0.61

 toug

-0.60

oos

-0.60

chairs

-0.60

POSITIVE LOGITS

 achieved

1.12

 elusive

1.04

 achievable

0.99

 attained

0.93

 outwe

0.91

 depended

0.90

 attain

0.88

chieve

0.87

¥µ

0.86

 accol

0.84

Activations Density 0.579%

phrases related to success and achievement

No Comments

No Known Activations