INDEX

Explanations

phrases indicating readiness or preparation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate readiness or preparedness for an action or event

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

audi

-0.69

UA

-0.69

hai

-0.69

hes

-0.69

Viol

-0.67

jiang

-0.67

gypt

-0.66

quickShipAvailable

-0.66

Originally

-0.65

ral

-0.64

POSITIVE LOGITS

 fire

0.76

 arrival

0.70

 welcoming

0.70

 launch

0.68

ailability

0.67

 wildfire

0.67

 sacrific

0.67

vironment

0.67

 bend

0.67

 ignite

0.66

Activations Density 0.067%

phrases indicating readiness or preparation

phrases that indicate readiness or preparedness for an action or event

No Comments

No Known Activations