INDEX

Explanations

positive attributes or actions related to morality or ethics

oai_token-act-pair · gpt-3.5-turbo

phrases or concepts associated with "good faith" or general goodness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ĸļ

-0.80

eters

-0.72

olate

-0.71

 Sturgeon

-0.70

otom

-0.70

_>

-0.68

EStream

-0.67

agos

-0.67

 Canaver

-0.66

hyde

-0.66

POSITIVE LOGITS

 intentions

1.27

 Samar

1.23

 luck

1.19

bye

1.18

reads

1.14

 deeds

1.13

 deed

1.12

ol

1.10

 fortune

1.05

enough

1.04

Activations Density 0.068%

positive attributes or actions related to morality or ethics

phrases or concepts associated with "good faith" or general goodness

No Comments

No Known Activations