INDEX

Explanations

phrases expressing strong opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

oled

-0.77

blem

-0.76

omsky

-0.72

oling

-0.71

=~=~

-0.69

ositories

-0.68

ernels

-0.67

oÄŁan

-0.67

lia

-0.63

Newsletter

-0.62

POSITIVE LOGITS

 goodbye

1.14

bye

0.98

 aloud

0.84

lihood

0.75

 amen

0.69

 publicly

0.69

 hello

0.67

 loudly

0.62

YN

0.62

 sorry

0.61

Activations Density 0.065%

phrases expressing strong opinions or beliefs

No Comments

No Known Activations