INDEX

Explanations

names of specific locations or entities like schools, companies, and cities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, especially related to locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

lees

-0.75

riages

-0.73

nels

-0.68

urrencies

-0.68

assies

-0.68

iddles

-0.67

anwhile

-0.67

 Merchants

-0.66

 embassies

-0.66

sites

-0.66

POSITIVE LOGITS

 staffer

0.87

 variant

0.84

 spokesperson

0.84

 endorsement

0.81

ussian

0.78

 standpoint

0.78

 spokeswoman

0.76

statement

0.75

 representative

0.74

 colleague

0.73

Activations Density 0.709%

names of specific locations or entities like schools, companies, and cities

proper nouns, especially related to locations and organizations

No Comments

No Known Activations