INDEX

Explanations

references to philosophical concepts and arguments

oai_token-act-pair · gpt-3.5-turbo

scholarly claims and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

lbs

-0.84

 Canaveral

-0.83

Emergency

-0.79

VIP

-0.76

Health

-0.72

 Dubai

-0.71

 snapped

-0.70

RELATED

-0.69

SHARE

-0.69

health

-0.69

POSITIVE LOGITS

 epist

1.27

 methodological

1.26

 empir

1.20

 empirical

1.16

 eluc

1.15

 philosophers

1.11

 conject

1.06

 philosoph

1.03

 presupp

1.01

 scholarly

1.00

Activations Density 1.125%

references to philosophical concepts and arguments

scholarly claims and arguments

No Comments

No Known Activations