INDEX

Explanations

references to the Naval Academy and Naval-related terms

oai_token-act-pair · gpt-3.5-turbo

references to naval institutions and military contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oned

-1.00

à

-0.86

oning

-0.82

upon

-0.78

heimer

-0.77

onement

-0.76

hov

-0.76

-0.75

iang

-0.70

DonaldTrump

-0.69

POSITIVE LOGITS

odon

0.90

aval

0.88

 vessels

0.84

 SEAL

0.83

 bombardment

0.82

 Naval

0.79

 sailor

0.78

 ship

0.78

 blockade

0.78

boat

0.77

Activations Density 0.015%

references to the Naval Academy and Naval-related terms

references to naval institutions and military contexts

No Comments

No Known Activations