INDEX

Explanations

phrases related to completing tasks or achieving goals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" indicating intention or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

soDeliveryDate

-0.51

listed

-0.51

quickShipAvailable

-0.44

 netted

-0.41

 costing

-0.41

 millenn

-0.40

anooga

-0.40

 nomine

-0.40

Got

-0.39

_.

-0.39

POSITIVE LOGITS

 avoid

0.75

ggles

0.73

 compensate

0.72

 maximize

0.71

 achieve

0.69

 minimize

0.68

othy

0.68

 defend

0.67

 protect

0.67

 relieve

0.67

Activations Density 0.716%

phrases related to completing tasks or achieving goals

instances of the word "to" indicating intention or purpose

No Comments

No Known Activations