INDEX

Explanations

names of locations and organizations, especially those that are newsworthy

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and places

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

 Wally

-0.94

 Wonderland

-0.91

 Lovecraft

-0.90

 Grateful

-0.84

 Hitch

-0.83

 Turtles

-0.83

 Gravity

-0.82

ãĤ´ãĥ³

-0.82

 Cary

-0.82

 Yankee

-0.81

POSITIVE LOGITS

akh

1.18

ifa

1.15

abi

1.15

iya

1.15

awi

1.14

afi

1.05

zbollah

1.02

azi

1.01

Syrian

1.01

habi

1.01

Activations Density 0.408%

names of locations and organizations, especially those that are newsworthy

proper nouns, specifically names and places

No Comments

No Known Activations