INDEX

Explanations

locations or places, particularly those related to political events or conflicts

oai_token-act-pair · gpt-3.5-turbo

geographical locations and regions mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 crank

-0.67

 brakes

-0.64

 latch

-0.64

 excuses

-0.64

Knight

-0.64

 carbohyd

-0.63

 technician

-0.62

=-=-=-=-

-0.60

guy

-0.60

 censored

-0.59

POSITIVE LOGITS

 Peninsula

0.88

 Meadows

0.86

 Province

0.86

 Valley

0.85

 Island

0.84

arat

0.83

edd

0.82

 Junction

0.81

 Resort

0.80

 district

0.80

Activations Density 0.324%

locations or places, particularly those related to political events or conflicts

geographical locations and regions mentioned in the text

No Comments

No Known Activations