INDEX

Explanations

instances of the word "forced to" in a sentence

oai_token-act-pair · gpt-3.5-turbo

instances of being "forced to" do something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

quickShipAvailable

-0.84

 Emerging

-0.77

anooga

-0.73

calling

-0.73

 Blueprint

-0.71

 Compass

-0.69

soType

-0.69

 Used

-0.69

initialized

-0.68

 Needs

-0.67

POSITIVE LOGITS

 endure

1.16

 undertake

1.05

 fend

1.03

 abandon

1.02

 confront

1.02

 wear

1.01

 compete

0.99

 undergo

0.98

 perform

0.98

 obey

0.98

Activations Density 0.098%

instances of the word "forced to" in a sentence

instances of being "forced to" do something

No Comments

No Known Activations