INDEX

Explanations

locations or place names

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or entities

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

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

earance

-0.93

acters

-0.88

geries

-0.81

onies

-0.81

orously

-0.79

enegger

-0.75

 spoken

-0.74

cific

-0.74

ibliography

-0.74

olkien

-0.74

POSITIVE LOGITS

 Airlines

1.11

 Airways

1.07

 Avenue

1.06

 Oaks

1.04

 Tire

1.03

 Creek

1.03

 Labs

1.02

 Brewing

1.01

 Solutions

1.00

 Broadcasting

1.00

Activations Density 0.352%

locations or place names

references to specific locations or entities

No Comments

No Known Activations