INDEX

Explanations

references to the company or brand "Pan"

oai_token-act-pair · gpt-3.5-turbo

references to "Pan" or "Pan American."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enance

-0.75

itability

-0.71

UGH

-0.67

 minded

-0.66

 Judd

-0.65

CTR

-0.60

 confir

-0.60

OUND

-0.59

itably

-0.58

RON

-0.58

POSITIVE LOGITS

acea

1.33

orama

1.33

tera

1.22

zers

1.15

asonic

1.05

iola

1.00

era

0.99

aman

0.99

handle

0.98

ahi

0.96

Activations Density 0.018%

references to the company or brand "Pan"

references to "Pan" or "Pan American."

No Comments

No Known Activations