INDEX

Explanations

phrases related to replies or responses in a conversation

oai_token-act-pair · gpt-3.5-turbo

instances of strong emotional responses or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

soDeliveryDate

-1.05

çīĪ

-0.67

 Travels

-0.60

MpServer

-0.59

 visiting

-0.59

roups

-0.58

Torrent

-0.58

 rumors

-0.57

icycle

-0.57

GROUP

-0.56

POSITIVE LOGITS

 replied

1.96

 replies

1.70

 answered

1.68

 reply

1.68

 responded

1.57

 answer

1.51

Answer

1.45

 responds

1.41

 answers

1.37

 Answer

1.32

Activations Density 0.382%

phrases related to replies or responses in a conversation

instances of strong emotional responses or statements

No Comments

No Known Activations