INDEX

Explanations

locations or buildings with the word "Center" in their names

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

wcsstore

-0.71

 Luthor

-0.69

colour

-0.68

cia

-0.67

eting

-0.67

ubuntu

-0.66

ixel

-0.65

à¥

-0.63

olean

-0.61

crop

-0.61

POSITIVE LOGITS

pieces

0.89

 pamph

0.80

piece

0.77

 staffed

0.72

stadt

0.71

 located

0.70

ologies

0.70

 fielder

0.70

 billing

0.68

 Plaza

0.68

Activations Density 0.030%

locations or buildings with the word "Center" in their names

No Comments

No Known Activations