INDEX

Explanations

words related to locations, specifically related to the Atlantic area

oai_token-act-pair · gpt-3.5-turbo

references to the Atlantic region

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

advertising

-0.92

giving

-0.83

older

-0.78

baugh

-0.78

DEN

-0.74

etsk

-0.74

byn

-0.73

ming

-0.72

INGTON

-0.71

escal

-0.71

POSITIVE LOGITS

 Ocean

1.26

 Yards

0.99

 Coast

0.96

 Highlands

0.96

 Treaty

0.93

Ocean

0.90

 Monthly

0.89

 Wire

0.87

 City

0.83

 Shore

0.82

Activations Density 0.047%

words related to locations, specifically related to the Atlantic area

references to the Atlantic region

No Comments

No Known Activations