INDEX

Explanations

alcoholic beverages and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to classifications or categorizations

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

 assorted

-0.56

arthy

-0.50

 suspic

-0.49

MODE

-0.49

 inverse

-0.48

¥

-0.47

COLOR

-0.47

 helic

-0.47

 perspect

-0.46

 Undead

-0.46

POSITIVE LOGITS

nor

2.52

 anymore

2.21

nor

1.87

 whatsoever

1.49

yet

1.44

 unless

1.30

 anywhere

1.24

Nor

1.23

 slightest

1.20

unless

1.17

Activations Density 0.921%

alcoholic beverages and related terms

terms related to classifications or categorizations

No Comments

No Known Activations