INDEX

Explanations

phrases related to changes in numerical data over time

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" along with numerical data related to time periods

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

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

ens

-0.79

 ingred

-0.69

emo

-0.67

 minded

-0.65

 looms

-0.64

ById

-0.62

ALSE

-0.62

ATHER

-0.62

sonian

-0.62

onym

-0.59

POSITIVE LOGITS

1.25

1.24

1.23

1.21

1.20

1.18

1.15

Activations Density 0.156%

phrases related to changes in numerical data over time

occurrences of the word "in" along with numerical data related to time periods

No Comments

No Known Activations