INDEX

Explanations

locations, particularly states in the United States

oai_token-act-pair · gpt-3.5-turbo

references to specific U.S. states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rings

-0.78

deck

-0.76

byn

-0.73

colo

-0.73

 behav

-0.70

BOOK

-0.69

chel

-0.67

lihood

-0.66

fare

-0.65

seller

-0.65

POSITIVE LOGITS

 Springs

1.05

 State

0.98

 Instruments

0.98

 Tech

0.96

 Avenue

0.90

 Highlands

0.90

 Railroad

0.89

sylvania

0.89

Gov

0.85

 Rapids

0.84

Activations Density 0.132%

locations, particularly states in the United States

references to specific U.S. states

No Comments

No Known Activations