INDEX

Explanations

comparative statements emphasizing additional information or importance

oai_token-act-pair · gpt-3.5-turbo

the word "more" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Enlarge

-0.82

atan

-0.71

ļé

-0.69

xtap

-0.68

 Classification

-0.67

 Passage

-0.66

boy

-0.65

 ILCS

-0.65

itudes

-0.62

 Reconstruction

-0.62

POSITIVE LOGITS

 than

1.23

 importantly

1.20

ado

1.01

 Than

0.93

 stringent

0.90

 sophisticated

0.87

 efficient

0.82

than

0.82

 expensive

0.81

 mature

0.80

Activations Density 0.138%

comparative statements emphasizing additional information or importance

the word "more" in various contexts

No Comments

No Known Activations