INDEX

Explanations

specific references to the term "Lost" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the term "Lost" associated with various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 pist

-0.76

 enthusi

-0.74

 grocer

-0.69

 respons

-0.67

emaker

-0.67

eter

-0.64

rad

-0.63

PET

-0.62

elli

-0.62

 rounds

-0.61

POSITIVE LOGITS

 Lost

3.72

Lost

3.11

lost

2.48

 lost

1.70

 Forgotten

1.54

 Shattered

1.43

 Lose

1.39

 Gained

1.36

 Missing

1.34

 Haunted

1.33

Activations Density 0.022%

specific references to the term "Lost" in various contexts

references to the term "Lost" associated with various contexts

No Comments

No Known Activations