INDEX

Explanations

names of media outlets and individuals in journalism

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OUP

-0.67

 âĵĺ

-0.65

ointment

-0.64

ardless

-0.63

 secondly

-0.63

idity

-0.60

UCT

-0.58

 besides

-0.57

\<

-0.57

 Freeze

-0.57

POSITIVE LOGITS

 attest

1.18

 pointed

1.04

 explained

1.01

 alluded

1.01

 explains

0.93

 aptly

0.93

 demonstrated

0.91

 eloqu

0.90

 demonstrates

0.88

 rightly

0.86

Activations Density 0.187%

names of media outlets and individuals in journalism

references to notable individuals and their contributions

No Comments

No Known Activations