INDEX

Explanations

locations related to the Hudson River and nearby areas

oai_token-act-pair · gpt-3.5-turbo

references to the Hudson River and its related areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ISTER

-0.77

here

-0.74

fully

-0.73

book

-0.72

late

-0.71

vol

-0.70

eper

-0.70

chio

-0.69

nz

-0.69

cious

-0.67

POSITIVE LOGITS

 Yards

1.07

 Hudson

0.94

 Strait

0.81

 Valley

0.79

Bay

0.78

 Falls

0.77

 Hawk

0.75

 River

0.74

Moh

0.74

 Neck

0.72

Activations Density 0.014%

locations related to the Hudson River and nearby areas

references to the Hudson River and its related areas

No Comments

No Known Activations