INDEX

Explanations

words related to formal agreements or contracts

oai_token-act-pair · gpt-3.5-turbo

instances of formal agreements or contracts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

gun

-0.79

bull

-0.77

asus

-0.75

culus

-0.71

castle

-0.71

milo

-0.70

ãĥ©ãĥ³

-0.66

crow

-0.66

stocks

-0.65

gone

-0.64

POSITIVE LOGITS

reements

1.15

 agreement

1.14

 Agreement

1.10

 agreements

1.07

reement

0.99

 treaties

0.95

 treaty

0.95

 negotiated

0.92

ually

0.89

 agre

0.85

Activations Density 0.036%

words related to formal agreements or contracts

instances of formal agreements or contracts

No Comments

No Known Activations