INDEX

Explanations

locations, distances, and directions

oai_token-act-pair · gpt-3.5-turbo

specific geographical locations and distances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

phrine

-0.76

ombies

-0.72

auer

-0.67

ItemTracker

-0.66

Reviewer

-0.65

 facult

-0.65

 Responsibility

-0.64

onduct

-0.63

umers

-0.62

obal

-0.60

POSITIVE LOGITS

 miles

1.21

 northwest

1.05

 mile

1.03

 southeast

1.02

 northeast

1.02

 southwest

1.01

 blocks

0.99

 east

0.99

 north

0.99

 south

0.97

Activations Density 0.130%

locations, distances, and directions

specific geographical locations and distances

No Comments

No Known Activations