INDEX

Explanations

mentions of fairness in various contexts

oai_token-act-pair · gpt-3.5-turbo

monetary values or financial figures

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

 skelet

-0.81

iannopoulos

-0.68

icio

-0.68

olesc

-0.67

ographed

-0.67

handled

-0.67

 Valhalla

-0.64

 pestic

-0.64

 mathemat

-0.63

iggurat

-0.63

POSITIVE LOGITS

Â¢

1.13

¹

0.84

osal

0.84

ï¸ı

0.78

rocal

0.73

atoon

0.73

TION

0.72

hl

0.72

roid

0.70

 cents

0.70

Activations Density 0.003%

mentions of fairness in various contexts

monetary values or financial figures

No Comments

No Known Activations