INDEX

Explanations

phrases indicating speaking or quoting, typically at the end of a sentence

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "he said" conveying reported speech

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

taboola

-0.68

arnaev

-0.67

Bed

-0.67

andom

-0.66

Photos

-0.62

ertain

-0.62

tains

-0.62

Admin

-0.61

advertising

-0.61

cerning

-0.61

POSITIVE LOGITS

 goodbye

0.79

 bluntly

0.73

 sarcast

0.72

 emphatically

0.67

 passionately

0.67

 afterwards

0.65

 Schn

0.65

 afterward

0.64

 aloud

0.62

 Rivera

0.61

Activations Density 0.147%

phrases indicating speaking or quoting, typically at the end of a sentence

instances of the phrase "he said" conveying reported speech

No Comments

No Known Activations