INDEX

Explanations

proper nouns, titles, and nicknames

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

ython

-0.63

omas

-0.63

ertodd

-0.58

 Warriors

-0.57

 NAACP

-0.57

gap

-0.56

arna

-0.56

atana

-0.56

abases

-0.55

onential

-0.55

POSITIVE LOGITS

 wont

1.33

 nowadays

0.83

 presently

0.77

displayText

0.72

 hereafter

0.71

 today

0.70

_.

0.69

pring

0.67

isSpecialOrderable

0.67

 Offic

0.67

Activations Density 0.156%

proper nouns, titles, and nicknames

No Comments

No Known Activations