INDEX

Explanations

phrases related to specific locations and events

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

writer

-0.82

writing

-0.78

reader

-0.78

lance

-0.78

bery

-0.77

rar

-0.76

ority

-0.76

istant

-0.75

pherd

-0.75

ibilities

-0.73

POSITIVE LOGITS

 Massacre

1.09

 Airport

1.01

 Incident

0.94

 airport

0.94

 Declaration

0.93

 Dome

0.85

 Station

0.83

 Treaty

0.83

 earthquake

0.82

 Landing

0.81

Activations Density 0.325%

phrases related to specific locations and events

references to specific locations or historical events

No Comments

No Known Activations