INDEX

Explanations

years and time periods

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate historical contexts or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

channelAvailability

-0.69

 therein

-0.65

plates

-0.64

REF

-0.62

oother

-0.59

ļéĨĴ

-0.58

unique

-0.58

Spot

-0.58

»Ĵ

-0.58

istrate

-0.57

POSITIVE LOGITS

1.52

1.50

1.49

1.48

1.47

Activations Density 0.168%

years and time periods

phrases that indicate historical contexts or time periods

No Comments

No Known Activations