INDEX

Explanations

references to specific terrorist organizations and leaders

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Laur

-0.68

livious

-0.66

 Poles

-0.65

 Wilde

-0.65

 Warp

-0.64

EVE

-0.64

 crochet

-0.64

 erection

-0.62

 Victoria

-0.61

 Polar

-0.60

POSITIVE LOGITS

azeera

1.27

aeda

1.11

aghd

1.00

abi

0.98

qqa

0.98

awi

0.96

adr

0.95

adi

0.90

aq

0.90

aida

0.89

Activations Density 0.079%

references to specific terrorist organizations and leaders

No Comments

No Known Activations