INDEX

Explanations

personal pronouns indicating possession or connection

oai_token-act-pair · gpt-3.5-turbo

instances of the word "your."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ilts

-0.76

trak

-0.73

ylum

-0.73

raq

-0.72

Lago

-0.71

ega

-0.70

-0.69

asia

-0.68

rix

-0.68

oldemort

-0.67

POSITIVE LOGITS

own

1.22

 mileage

1.01

 favorite

1.01

 favourite

1.00

selves

0.89

 opponent

0.87

 choice

0.86

 guys

0.84

ths

0.82

 imagination

0.82

Activations Density 0.109%

personal pronouns indicating possession or connection

instances of the word "your."

No Comments

No Known Activations