INDEX

Explanations

words related to the abbreviation "ACT"

oai_token-act-pair · gpt-3.5-turbo

references to the ACT (Australian Capital Territory) and related initiatives or projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ppelin

-0.80

pper

-0.76

 Canaver

-0.74

chief

-0.71

ptin

-0.71

xual

-0.70

ovych

-0.68

comfort

-0.67

condition

-0.67

 accompanying

-0.67

POSITIVE LOGITS

ional

1.06

ION

1.05

IONS

1.03

UAL

0.99

IVE

0.93

IV

0.86

ivity

0.85

YL

0.85

ACT

0.81

 CLIENT

0.78

Activations Density 0.007%

words related to the abbreviation "ACT"

references to the ACT (Australian Capital Territory) and related initiatives or projects

No Comments

No Known Activations