INDEX

Explanations

mentions of the name "Meg"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Meg" and its variations in relation to a specific context or subject

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

âķĲâķĲ

-0.76

 FIRE

-0.70

 AMERICA

-0.66

ãģį

-0.63

 Maduro

-0.62

 governors

-0.62

 conditioning

-0.61

âĢİ

-0.61

xual

-0.61

 principals

-0.61

POSITIVE LOGITS

atron

1.04

abyte

1.01

abus

0.97

alon

0.91

aton

0.89

azine

0.88

acy

0.87

apolis

0.86

awatts

0.85

antic

0.83

Activations Density 0.013%

mentions of the name "Meg"

references to the term "Meg" and its variations in relation to a specific context or subject

No Comments

No Known Activations