INDEX

Explanations

proper nouns used in news or journalism contexts

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Updates

-0.77

 Household

-0.74

 Bots

-0.70

AAA

-0.70

 Packs

-0.69

 RELEASE

-0.69

 Hyundai

-0.67

 BASE

-0.67

 Emblem

-0.66

 FIRST

-0.66

POSITIVE LOGITS

asser

1.16

aiman

1.12

essel

1.11

aylor

1.11

arkin

1.10

iggs

1.09

enson

1.09

iggins

1.07

ellar

1.06

utton

1.06

Activations Density 0.167%

proper nouns used in news or journalism contexts

No Comments

No Known Activations