INDEX

Explanations

phrases related to specific comparison or consideration of various subjects

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 tatt

-0.69

 suspic

-0.60

kan

-0.60

 Guth

-0.58

aden

-0.57

 Ezek

-0.54

 Sieg

-0.54

 nood

-0.53

 Dahl

-0.52

 Semin

-0.51

POSITIVE LOGITS

 thereto

1.07

to

0.91

 regards

0.84

to

0.73

inction

0.70

rait

0.65

cussion

0.64

tains

0.64

erence

0.64

 towards

0.63

Activations Density 0.045%

phrases related to specific comparison or consideration of various subjects

No Comments

No Known Activations