INDEX

Explanations

keywords related to programming syntax, function usage, and code operations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating purpose or function

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

living

-0.80

 Worth

-0.80

icipated

-0.72

armed

-0.70

partisan

-0.70

going

-0.69

soDeliveryDate

-0.69

hillary

-0.68

ylum

-0.66

beer

-0.66

POSITIVE LOGITS

 simulate

1.49

 simplify

1.39

ggles

1.39

 automate

1.35

 manipulate

1.33

 emulate

1.33

 modify

1.30

 optimize

1.30

 differentiate

1.29

 determine

1.27

Activations Density 0.202%

keywords related to programming syntax, function usage, and code operations

phrases indicating purpose or function

No Comments

No Known Activations