INDEX

Explanations

locations and organizations mentioned in news or articles

oai_token-act-pair · gpt-3.5-turbo

mentions of news organizations or related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 brilliance

-0.67

 flavour

-0.66

 mould

-0.64

 flavours

-0.62

isations

-0.61

 realise

-0.60

 realised

-0.60

BBC

-0.60

 maths

-0.59

 favourites

-0.59

POSITIVE LOGITS

 sheriff

0.71

 Parkway

0.68

 Fresno

0.67

Oregon

0.66

 Harbor

0.65

 Boone

0.64

 FEMA

0.64

 courthouse

0.64

 Correctional

0.63

Portland

0.63

Activations Density 4.769%

locations and organizations mentioned in news or articles

mentions of news organizations or related entities

No Comments

No Known Activations