INDEX

Explanations

mentions of technical specifications related to dual systems or components

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

FORE

-0.77

orio

-0.75

 Warehouse

-0.70

UFF

-0.70

################

-0.67

utics

-0.62

brance

-0.62

à¥

-0.59

ERE

-0.59

avid

-0.58

POSITIVE LOGITS

ples

0.96

ity

0.88

 sided

0.87

xes

0.86

shock

0.83

Shock

0.81

role

0.80

fold

0.80

tone

0.80

 elig

0.79

Activations Density 0.026%

mentions of technical specifications related to dual systems or components

No Comments

No Known Activations