INDEX

Explanations

information related to specific events or locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

mentions of humanitarian issues and crises

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

 folks

-0.74

 Boone

-0.72

 Whitman

-0.72

 Sloan

-0.71

Ohio

-0.70

 Lamar

-0.70

 Rollins

-0.69

Indiana

-0.68

BYU

-0.68

 Offense

-0.68

POSITIVE LOGITS

 organisers

1.02

 organised

0.92

 analyse

0.91

 favour

0.91

 apologise

0.90

 Fifa

0.90

 favourable

0.90

 practise

0.89

 authorised

0.89

 recognise

0.88

Activations Density 2.211%

information related to specific events or locations mentioned in news articles

mentions of humanitarian issues and crises

No Comments

No Known Activations